While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood. Existing analyses primarily focus on attention mechanisms and downstream performance, leaving the evolution of representation geometry largely unexplored. In this work, we present Transformer Geometry Observatory-II (TGO-II), a representation geometry analysis framework designed to investigate how Transformer representations evolve during supervised training. TGO-II analyzes Vision Transformer (ViT-Small/16) representations using Centered Kernel Alignment (CKA), Singular Vector Canonical Correlation Analysis (SVCCA), Two-Nearest Neighbor Intrinsic Dimensionality (TwoNN-ID), and token covariance analysis. Our experiments reveal three key observations. First, both CKA and SVCCA progressively decrease throughout training, indicating increasing representational specialization across Transformer layers. Second, intrinsic dimensionality consistently increases before stabilizing, suggesting progressive expansion of the representation manifold into a larger set of locally accessible degrees of freedom. Third, token covariance and coupling analyses demonstrate that strong token interaction structure persists throughout training, challenging the hypothesis that increasing representational complexity arises primarily from progressive token independence. These findings suggest that representation complexity and layer specialization emerge simultaneously during training. Manifold expansion appears to occur without token decoupling. Together, these observations motivate a new hypothesis in which Vision Transformers increase representational complexity through progressively richer transformations while preserving strong token interaction structure during learning.
展开完整摘要收起摘要↓
While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood. Existing analyses primarily focus on attention mechanisms and downstream performance, leaving the evolution of representation geometry largely unexplored. In this work, we present Transformer Geometry Observatory-II (TGO-II), a representation geometry analysis framework designed to investigate how Transformer representations evolve during supervised training. TGO-II analyzes Vision Transformer (ViT-Small/16) representations using Centered Kernel Alignment (CKA), Singular Vector Canonical Correlation Analysis (SVCCA), Two-Nearest Neighbor Intrinsic Dimensionality (TwoNN-ID), and token covariance analysis. Our experiments reveal three key observations. First, both CKA and SVCCA progressively decrease throughout training, indicating increasing representational specialization across Transformer layers. Second, intrinsic dimensionality consistently increases before stabilizing, suggesting progressive expansion of the representation manifold into a larger set of locally accessible degrees of freedom. Third, token covariance and coupling analyses demonstrate that strong token interaction structure persists throughout training, challenging the hypothesis that increasing representational complexity arises primarily from progressive token independence. These findings suggest that representation complexity and layer specialization emerge simultaneously during training. Manifold expansion appears to occur without token decoupling. Together, these observations motivate a new hypothesis in which Vision Transformers increase representational complexity through progressively richer transformations while preserving strong token interaction structure during learning.
Natural Language Processing (NLP) has traditionally been published in its core disciplinary venues like ACL. However, advances in Large Language Models (LLMs) has led to a blurring of the disciplinary lines between NLP and general Machine Learning (ML), with authors regularly publishing in venues from both fields. Here, we ask whether the disciplinary center of gravity is shifting. Using NLP research published from 2010 to 2026 and studies of both established and new authors, we find that a migration is taking place. First, comparing the pre- and post-LLM eras, established authors lost 19.2pp of share at flagship *ACL main-conference tracks while gaining 14.8pp in the newer Findings tracks, and general ML venues rose 8.6pp, even when adjusting for parallel growth in the fields. Second, among newer authors who debut with at least three first-author NLP-topic papers, the share whose work appears mostly at *ACL venues fell from 84% (2019) to 74% (2024), while the share appearing mostly at general ML venues rose from 5% to 21%. Using causal inference techniques, we estimate that these general ML venues confer a significant citation premium, which influences venue selection. Together, these results point to a significant shift in where NLP research is published.
展开完整摘要收起摘要↓
Natural Language Processing (NLP) has traditionally been published in its core disciplinary venues like ACL. However, advances in Large Language Models (LLMs) has led to a blurring of the disciplinary lines between NLP and general Machine Learning (ML), with authors regularly publishing in venues from both fields. Here, we ask whether the disciplinary center of gravity is shifting. Using NLP research published from 2010 to 2026 and studies of both established and new authors, we find that a migration is taking place. First, comparing the pre- and post-LLM eras, established authors lost 19.2pp of share at flagship *ACL main-conference tracks while gaining 14.8pp in the newer Findings tracks, and general ML venues rose 8.6pp, even when adjusting for parallel growth in the fields. Second, among newer authors who debut with at least three first-author NLP-topic papers, the share whose work appears mostly at *ACL venues fell from 84% (2019) to 74% (2024), while the share appearing mostly at general ML venues rose from 5% to 21%. Using causal inference techniques, we estimate that these general ML venues confer a significant citation premium, which influences venue selection. Together, these results point to a significant shift in where NLP research is published.
Language models are increasingly used to quantify cultural phenomena, but what makes such measurement distinctively cultural? This paper argues that NLP work on culture is a material-discursive practice: the apparatus — model, data, annotation, evaluation — participates in constituting the cultural reality it measures, rather than passively recording it. Drawing on Karen Barad's concept of the agential cut — the contingent boundary between phenomenon and instrument — I show that the apparatus's substantive design choices draw such boundaries, and that the boundary is entangled from the start because language models have already internalized much of the cultural material they measure. I illustrate this through three case studies on television and film dialogue (measuring structure, interaction, and deviation) and three examinations of the apparatus itself (erasure of cultural markers, attunement to historical material, and agency in an agentic workflow). This big picture analysis proposes a research program that is theory-driven, empirically rigorous, and culturally contingent, treating each agential cut as a conscious commitment, at once methodological and ethical.
展开完整摘要收起摘要↓
Language models are increasingly used to quantify cultural phenomena, but what makes such measurement distinctively cultural? This paper argues that NLP work on culture is a material-discursive practice: the apparatus — model, data, annotation, evaluation — participates in constituting the cultural reality it measures, rather than passively recording it. Drawing on Karen Barad's concept of the agential cut — the contingent boundary between phenomenon and instrument — I show that the apparatus's substantive design choices draw such boundaries, and that the boundary is entangled from the start because language models have already internalized much of the cultural material they measure. I illustrate this through three case studies on television and film dialogue (measuring structure, interaction, and deviation) and three examinations of the apparatus itself (erasure of cultural markers, attunement to historical material, and agency in an agentic workflow). This big picture analysis proposes a research program that is theory-driven, empirically rigorous, and culturally contingent, treating each agential cut as a conscious commitment, at once methodological and ethical.
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.
展开完整摘要收起摘要↓
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.
作者Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li
Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing editors mainly emphasize edit reliability and long-horizon stability, but rarely control the semantic boundary of each edit. Our pilot analyses of post-edit behaviors and internal neuronal activities reveal a scope gap behind reliable edits: instance-level success neither guarantees transfer to valid cross-modal variants nor prevents leakage to unrelated inputs, while edit-related cross-modal responses concentrate in deeper semantic layers. Therefore, we formulate Edit-Scoped Generalization, reframing online MLLM editing from merely correcting an instance to controlling the propagation boundary of each edit. To this end, we propose ScopeEdit, a scope-aware online editor that decomposes each update into a modality-local absorption branch and an evidence-gated shared generalization branch. The local branch supports stable edit absorption, whereas the shared branch enables cross-modal propagation only when visual and textual evidence are sufficiently aligned. Both branches perform scope-separated write geometries in orthogonal low-rank spaces and maintain branch-wise preconditioners via Sherman--Morrison recursions, yielding constant per-edit overhead. Extensive experiments across diverse benchmarks, long-horizon edit streams, MLLM backbones, real-world VLKEB scenarios, and complex vision-language architectures show that ScopeEdit consistently improves the trade-off between in-scope cross-modal transfer and out-of-scope locality, while preserving edit reliability, stability and online efficiency. Our code is available at https://github.com/lab-klc/ScopeEdit.
展开完整摘要收起摘要↓
Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing editors mainly emphasize edit reliability and long-horizon stability, but rarely control the semantic boundary of each edit. Our pilot analyses of post-edit behaviors and internal neuronal activities reveal a scope gap behind reliable edits: instance-level success neither guarantees transfer to valid cross-modal variants nor prevents leakage to unrelated inputs, while edit-related cross-modal responses concentrate in deeper semantic layers. Therefore, we formulate Edit-Scoped Generalization, reframing online MLLM editing from merely correcting an instance to controlling the propagation boundary of each edit. To this end, we propose ScopeEdit, a scope-aware online editor that decomposes each update into a modality-local absorption branch and an evidence-gated shared generalization branch. The local branch supports stable edit absorption, whereas the shared branch enables cross-modal propagation only when visual and textual evidence are sufficiently aligned. Both branches perform scope-separated write geometries in orthogonal low-rank spaces and maintain branch-wise preconditioners via Sherman--Morrison recursions, yielding constant per-edit overhead. Extensive experiments across diverse benchmarks, long-horizon edit streams, MLLM backbones, real-world VLKEB scenarios, and complex vision-language architectures show that ScopeEdit consistently improves the trade-off between in-scope cross-modal transfer and out-of-scope locality, while preserving edit reliability, stability and online efficiency. Our code is available at https://github.com/lab-klc/ScopeEdit.
作者Dat Quoc Nguyen, Thinh Pham, Chi Tran, Linh The Nguyen
In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT — the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among "base"-sized Vietnamese encoders and demonstrating strong cross-domain generalization. We release BamiBERT at: https://huggingface.co/Qualcomm-AI-Research/BamiBERT
展开完整摘要收起摘要↓
In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT — the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among "base"-sized Vietnamese encoders and demonstrating strong cross-domain generalization. We release BamiBERT at: https://huggingface.co/Qualcomm-AI-Research/BamiBERT
Large language model personas are increasingly used to approximate diverse users during early-stage visualization design, but it remains unclear whether persona-conditioned outputs reflect stable personality effects or artifacts of model choice and task framing. We examine this question across two visualization-relevant tasks: color assignment for abstract and concrete concepts, and chart-idiom preference ratings across task contexts. Using 43 Big Five profiles across GPT-4o-mini, GPT-4.1-mini, and GPT-5-mini, we find that personality-color coupling is highly model-configuration dependent: absent in GPT-4o-mini for all six concepts, consistent in GPT-4.1-mini across all six, and partial in GPT-5-mini for two of six. Concept type further shapes the signal: for abstract concepts, personality explains more hue variance than model identity, while concrete concepts show smaller and comparable effects. In chart choice, trait-aligned cluster aggregation produces stable top-idiom rankings across all nine cluster-context combinations, but a no-persona baseline recovers the same top choice in 8 of 9 model-context cells, indicating that task context drives rank-1 selection more than personality. These findings position LLM personas as exploratory probes for visualization design, not substitutes for human participants, and motivate multi-model testing, concept-type disaggregation, and no-persona baselines in future studies.
展开完整摘要收起摘要↓
Large language model personas are increasingly used to approximate diverse users during early-stage visualization design, but it remains unclear whether persona-conditioned outputs reflect stable personality effects or artifacts of model choice and task framing. We examine this question across two visualization-relevant tasks: color assignment for abstract and concrete concepts, and chart-idiom preference ratings across task contexts. Using 43 Big Five profiles across GPT-4o-mini, GPT-4.1-mini, and GPT-5-mini, we find that personality-color coupling is highly model-configuration dependent: absent in GPT-4o-mini for all six concepts, consistent in GPT-4.1-mini across all six, and partial in GPT-5-mini for two of six. Concept type further shapes the signal: for abstract concepts, personality explains more hue variance than model identity, while concrete concepts show smaller and comparable effects. In chart choice, trait-aligned cluster aggregation produces stable top-idiom rankings across all nine cluster-context combinations, but a no-persona baseline recovers the same top choice in 8 of 9 model-context cells, indicating that task context drives rank-1 selection more than personality. These findings position LLM personas as exploratory probes for visualization design, not substitutes for human participants, and motivate multi-model testing, concept-type disaggregation, and no-persona baselines in future studies.
Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold regularity of molecular LLMs. Our analysis shows that even a single edit can cause substantial performance drops on common molecular tasks, revealing a narrow local trust region and fragile sensitivity to structural changes. Since similar molecules tend to exhibit similar properties, In-Context Tuning (ICT), which anchors predictions on structurally similar molecules, offers a natural way to mitigate such fragility. Our experiments also examine whether ICT confers robustness under controlled structural perturbations, and the results suggest that it can partially expand the local trust region and offer a promising direction for stabilizing molecular LLMs against structural variation.
展开完整摘要收起摘要↓
Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold regularity of molecular LLMs. Our analysis shows that even a single edit can cause substantial performance drops on common molecular tasks, revealing a narrow local trust region and fragile sensitivity to structural changes. Since similar molecules tend to exhibit similar properties, In-Context Tuning (ICT), which anchors predictions on structurally similar molecules, offers a natural way to mitigate such fragility. Our experiments also examine whether ICT confers robustness under controlled structural perturbations, and the results suggest that it can partially expand the local trust region and offer a promising direction for stabilizing molecular LLMs against structural variation.
As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect and block malicious instructions sent to and from an LLM are an essential component of AI security. However, researchers conducting black-box adversarial emulation against production AI systems often struggle to determine whether a guardrail block or an LLM rejection has occurred. This distinction is important because the techniques used to bypass guardrails can differ substantially from those used to bypass LLM safety alignment, and has a material impact on attack technique selection and optimization. We propose the first black-box guardrail reconnaissance methodology, which detects the presence of a guardrail within a target AI system through behavioral monitoring of HTTP, lexical, and timing signals, assuming only black-box access and zero prior knowledge of the guardrail or AI system. Experiments demonstrate that our approach detects guardrail presence with 100% accuracy, with statistically significant behavioral separation between benign and malicious interactions (q < 0.001). Our approach further identifies the content categories a guardrail is designed to block, and distinguishes guardrail blocks from LLM rejection on unseen prompts with an average F1 score of 98%.
展开完整摘要收起摘要↓
As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect and block malicious instructions sent to and from an LLM are an essential component of AI security. However, researchers conducting black-box adversarial emulation against production AI systems often struggle to determine whether a guardrail block or an LLM rejection has occurred. This distinction is important because the techniques used to bypass guardrails can differ substantially from those used to bypass LLM safety alignment, and has a material impact on attack technique selection and optimization. We propose the first black-box guardrail reconnaissance methodology, which detects the presence of a guardrail within a target AI system through behavioral monitoring of HTTP, lexical, and timing signals, assuming only black-box access and zero prior knowledge of the guardrail or AI system. Experiments demonstrate that our approach detects guardrail presence with 100% accuracy, with statistically significant behavioral separation between benign and malicious interactions (q < 0.001). Our approach further identifies the content categories a guardrail is designed to block, and distinguishes guardrail blocks from LLM rejection on unseen prompts with an average F1 score of 98%.
Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt — drifting toward a false balance that treats settled science as one view among several. We test this across three open instruction-tuned models (Llama-3.1-8B, Qwen2.5-7B, Mistral-7B), three consensus-science domains (climate, vaccines, evolution), and single- and multi-turn settings, combining behavioral measurement with linear probing and activation patching. We do not observe sycophantic retreat. Instead, models show three distinct policies under the same skeptical pressure: reactive assertion, where consensus assertion increases rather than decreases (Llama); surface hedging, where tone softens while the position holds (Qwen); and non-response (Mistral). Pairwise judgments confirm the reactive shift is stance, not style (63.6%, p=.007), and a decomposition identifies increased consensus assertion, not false balance, as its driver (beta=+0.042 per dose, p<1e-77). Linear probes localize the divergence to middle layers — perfect separation in Llama and Qwen versus 72% in Mistral, with non-overlapping confidence intervals — indicating the non-responsive model does not linearly represent the skepticism signal at all. Crucially, this robustness does not transfer: it attenuates across domains and, in the safety-critical vaccine domain, can reverse, with myth-rebuttal weakening under skeptical pressure. We synthesize these into a four-way taxonomy separating active from accidental robustness, and argue that behavioral evaluation alone cannot distinguish a model that resists skepticism because it understands the signal from one that only appears to resist because it fails to perceive it.
展开完整摘要收起摘要↓
Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt — drifting toward a false balance that treats settled science as one view among several. We test this across three open instruction-tuned models (Llama-3.1-8B, Qwen2.5-7B, Mistral-7B), three consensus-science domains (climate, vaccines, evolution), and single- and multi-turn settings, combining behavioral measurement with linear probing and activation patching. We do not observe sycophantic retreat. Instead, models show three distinct policies under the same skeptical pressure: reactive assertion, where consensus assertion increases rather than decreases (Llama); surface hedging, where tone softens while the position holds (Qwen); and non-response (Mistral). Pairwise judgments confirm the reactive shift is stance, not style (63.6%, p=.007), and a decomposition identifies increased consensus assertion, not false balance, as its driver (beta=+0.042 per dose, p<1e-77). Linear probes localize the divergence to middle layers — perfect separation in Llama and Qwen versus 72% in Mistral, with non-overlapping confidence intervals — indicating the non-responsive model does not linearly represent the skepticism signal at all. Crucially, this robustness does not transfer: it attenuates across domains and, in the safety-critical vaccine domain, can reverse, with myth-rebuttal weakening under skeptical pressure. We synthesize these into a four-way taxonomy separating active from accidental robustness, and argue that behavioral evaluation alone cannot distinguish a model that resists skepticism because it understands the signal from one that only appears to resist because it fails to perceive it.
Vibe coding democratizes software development by allowing users to generate code via natural-language (NL) interaction with large language models (LLMs). However, the code is reliable only when it faithfully implements the user's intent, which is difficult and labor-intensive for users to validate. Existing validation methods either rely on LLM-assisted automated testing, which suffers from prompt ambiguity and model fallibility, or involve users only in partial software artifacts such as prompts and test cases, which may overlook corner cases and program details. Motivated by a bug study of LLM-generated code, we find that detailed human feedback is essential, as failures often stem from underspecified requirements or subtle semantic deviations. This paper presents verifiable literate programming (VLP), a human-in-the-loop framework designed to make the review/validation process of LLM-generated code accessible to users at all programming levels. At its core, VLP proposes unambiguous NL-based documentation as a readable intermediate layer between prompts and code. The documentation demonstrates concrete program semantics and enables users to provide feedback on potential intent-code mismatches. It supports human-involved, end-to-end repair and validation via three techniques: (i) an NL-style literate language with unambiguous syntax and mostly deterministic code-to-documentation translation, (ii) LLM-based fine-grained mismatch detection that uses trace links between prompts and documentation to focus users' review effort on suspicious documentation lines, and (iii) a verification module that leverages user-validated documentation to derive API-usage checks and formal properties, which are then verified against the generated code using model checking. Our evaluation shows that VLP improves code pass@1 from 28.7%-73.2% to 65.4%-93.5% with reasonable user effort.
展开完整摘要收起摘要↓
Vibe coding democratizes software development by allowing users to generate code via natural-language (NL) interaction with large language models (LLMs). However, the code is reliable only when it faithfully implements the user's intent, which is difficult and labor-intensive for users to validate. Existing validation methods either rely on LLM-assisted automated testing, which suffers from prompt ambiguity and model fallibility, or involve users only in partial software artifacts such as prompts and test cases, which may overlook corner cases and program details. Motivated by a bug study of LLM-generated code, we find that detailed human feedback is essential, as failures often stem from underspecified requirements or subtle semantic deviations. This paper presents verifiable literate programming (VLP), a human-in-the-loop framework designed to make the review/validation process of LLM-generated code accessible to users at all programming levels. At its core, VLP proposes unambiguous NL-based documentation as a readable intermediate layer between prompts and code. The documentation demonstrates concrete program semantics and enables users to provide feedback on potential intent-code mismatches. It supports human-involved, end-to-end repair and validation via three techniques: (i) an NL-style literate language with unambiguous syntax and mostly deterministic code-to-documentation translation, (ii) LLM-based fine-grained mismatch detection that uses trace links between prompts and documentation to focus users' review effort on suspicious documentation lines, and (iii) a verification module that leverages user-validated documentation to derive API-usage checks and formal properties, which are then verified against the generated code using model checking. Our evaluation shows that VLP improves code pass@1 from 28.7%-73.2% to 65.4%-93.5% with reasonable user effort.
作者Zhiren Gong, Zihao Zeng, Chau Yuen, Wei Yang Bryan Lim
Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior. This guides attribution, capability knockout, and model pruning downstream to operate by scoring each unit by the effect of ablation in isolation. Such first-order scoring is natural when component importance is additive, but becomes misleading when a transformer self-repairs: after a primary component is removed, a dormant backup can take over, muting the primary's measured effect while the backup itself appears irrelevant on the intact model. We recast this failure as a recovery task, conditional circuit completion, and introduce Conditional Co-Ablation (CoAx), a label-free, output-grounded score that asks how much each remaining unit's ablation effect grows once a primary set has been removed. This conditional growth exposes the second-order interaction that single-unit scores discard. On the GPT-2-small IOI circuit, CoAx raises backup-head recovery from 0.33 to 0.91 ROC-AUC, outperforming all baselines, including self-repair-aware gradient scores (best 0.82); counterfactual patching verifies that the recovered heads causally carry the repair. The same label-free procedure transfers to induction across eight models. Beyond discovery, the recovered backups correct self-repair-masked attribution, identify the components required for capability knockout, and yield repair-aware structured pruning scaling from 124M to 7B. Component importance is therefore not merely an isolated-unit property: in robust circuits, the components that matter can become visible only under the interventions that make them necessary.
展开完整摘要收起摘要↓
Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior. This guides attribution, capability knockout, and model pruning downstream to operate by scoring each unit by the effect of ablation in isolation. Such first-order scoring is natural when component importance is additive, but becomes misleading when a transformer self-repairs: after a primary component is removed, a dormant backup can take over, muting the primary's measured effect while the backup itself appears irrelevant on the intact model. We recast this failure as a recovery task, conditional circuit completion, and introduce Conditional Co-Ablation (CoAx), a label-free, output-grounded score that asks how much each remaining unit's ablation effect grows once a primary set has been removed. This conditional growth exposes the second-order interaction that single-unit scores discard. On the GPT-2-small IOI circuit, CoAx raises backup-head recovery from 0.33 to 0.91 ROC-AUC, outperforming all baselines, including self-repair-aware gradient scores (best 0.82); counterfactual patching verifies that the recovered heads causally carry the repair. The same label-free procedure transfers to induction across eight models. Beyond discovery, the recovered backups correct self-repair-masked attribution, identify the components required for capability knockout, and yield repair-aware structured pruning scaling from 124M to 7B. Component importance is therefore not merely an isolated-unit property: in robust circuits, the components that matter can become visible only under the interventions that make them necessary.
作者Congrui Du, Yang Zhang, Kaizhi Qian, Shiyu Chang
Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and a wide range of speech-specific instructions in addition to those supported by text LLMs. Existing SLM training approaches largely replicate the text LLM training paradigm by synthesizing large-scale speech pre-training and instruction-tuning datasets. However, this strategy is difficult to scale, since speech sequences are significantly longer than text sequences. In this paper, we propose SpeechCombine, an instruction-following speech language model trained without any instruction tuning, using only a single round of speech pre-training on 30k hours of data. Starting from a text LLM base model, we perform continuous pre-training on speech utterances to obtain a speech-adapted model, and then directly combine its weights with the weight difference between the instruction-tuned and base versions of the text LLM. Our results show that this simple combination strategy not only preserves the knowledge and capabilities of the original text LLM, but also effectively transfers them to the speech domain. These findings suggest a new direction for SLM training that avoids reliance on massive speech data.
展开完整摘要收起摘要↓
Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and a wide range of speech-specific instructions in addition to those supported by text LLMs. Existing SLM training approaches largely replicate the text LLM training paradigm by synthesizing large-scale speech pre-training and instruction-tuning datasets. However, this strategy is difficult to scale, since speech sequences are significantly longer than text sequences. In this paper, we propose SpeechCombine, an instruction-following speech language model trained without any instruction tuning, using only a single round of speech pre-training on 30k hours of data. Starting from a text LLM base model, we perform continuous pre-training on speech utterances to obtain a speech-adapted model, and then directly combine its weights with the weight difference between the instruction-tuned and base versions of the text LLM. Our results show that this simple combination strategy not only preserves the knowledge and capabilities of the original text LLM, but also effectively transfers them to the speech domain. These findings suggest a new direction for SLM training that avoids reliance on massive speech data.
作者Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J. Rodriguez-Martinez, Lorena Otero-Cerdeira
Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation. This paper evaluates whether four frontier Large Language Models (GPT, Claude Opus, Gemini, and GLM) can approximate expert judgment when grading short Linux/bash command responses. The study adopts a four-level cognitive taxonomy that combines cognitive complexity and operational impact, ranging from information retrieval (L1) and basic file manipulation (L2) to structural operations (L3) and advanced system management (L4). The models were tested with two prompt variants, a minimal baseline and a rubric-enhanced version, on 1200 real responses from second-year Computer Engineering students independently graded by three expert instructors. Gemini~3.0 Pro with rubric-guided prompting achieved the highest human-AI agreement (ICC(3,1) = 0.888, MAE = 0.10, Bland-Altman bias = -0.014). Agreement declined consistently as taxonomy level increased, with the largest discrepancies at higher levels. Across all models, rubric quality had a larger effect than provider choice, with structured prompts consistently improving agreement. These results show that question complexity is a reliable predictor of the difficulty LLMs face in grading accurately, and they establish a principled, taxonomy-based framework for determining which questions are suitable for AI-assisted grading and which require human review, while also providing a transferable evaluation protocol and prompt templates.
展开完整摘要收起摘要↓
Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation. This paper evaluates whether four frontier Large Language Models (GPT, Claude Opus, Gemini, and GLM) can approximate expert judgment when grading short Linux/bash command responses. The study adopts a four-level cognitive taxonomy that combines cognitive complexity and operational impact, ranging from information retrieval (L1) and basic file manipulation (L2) to structural operations (L3) and advanced system management (L4). The models were tested with two prompt variants, a minimal baseline and a rubric-enhanced version, on 1200 real responses from second-year Computer Engineering students independently graded by three expert instructors. Gemini~3.0 Pro with rubric-guided prompting achieved the highest human-AI agreement (ICC(3,1) = 0.888, MAE = 0.10, Bland-Altman bias = -0.014). Agreement declined consistently as taxonomy level increased, with the largest discrepancies at higher levels. Across all models, rubric quality had a larger effect than provider choice, with structured prompts consistently improving agreement. These results show that question complexity is a reliable predictor of the difficulty LLMs face in grading accurately, and they establish a principled, taxonomy-based framework for determining which questions are suitable for AI-assisted grading and which require human review, while also providing a transferable evaluation protocol and prompt templates.
Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is brittle, text similarity ignores structure, and an LLM judge is expensive, opaque, and non-deterministic. We address this with Object Aligner (OA), an open-source Python library that scores two JSON objects deterministically by recursively aligning their trees (the Hungarian algorithm for unordered collections, sequence alignment for ordered ones) and awarding partial credit at the granularity the schema declares. The Object Aligner is configured entirely through a set of JSON Schema extensions, so adapting it to a new task involves annotating a schema rather than writing code. Complex structured data, however, are rarely flat trees: records may form graphs or hypergraphs keyed by arbitrary identifiers, breaking the assumptions of prior similarity metrics. Our central contribution, referential alignment, closes this gap by inferring a bijection between gold and candidate identifiers and scoring every reference through it, so the score is invariant to relabeling. Since recovering this bijection exactly is graph isomorphism, the Object Aligner approximates it with Weisfeiler-Leman color refinement. An order-sensitive sequence regime targets ranking and planning. Since the same alignment localizes every mismatch, the Object Aligner emits ranked repair suggestions at no extra cost. Used as a reward inside the GEPA prompt optimizer, Object Aligner helps or stays neutral across all datasets.
展开完整摘要收起摘要↓
Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is brittle, text similarity ignores structure, and an LLM judge is expensive, opaque, and non-deterministic. We address this with Object Aligner (OA), an open-source Python library that scores two JSON objects deterministically by recursively aligning their trees (the Hungarian algorithm for unordered collections, sequence alignment for ordered ones) and awarding partial credit at the granularity the schema declares. The Object Aligner is configured entirely through a set of JSON Schema extensions, so adapting it to a new task involves annotating a schema rather than writing code. Complex structured data, however, are rarely flat trees: records may form graphs or hypergraphs keyed by arbitrary identifiers, breaking the assumptions of prior similarity metrics. Our central contribution, referential alignment, closes this gap by inferring a bijection between gold and candidate identifiers and scoring every reference through it, so the score is invariant to relabeling. Since recovering this bijection exactly is graph isomorphism, the Object Aligner approximates it with Weisfeiler-Leman color refinement. An order-sensitive sequence regime targets ranking and planning. Since the same alignment localizes every mismatch, the Object Aligner emits ranked repair suggestions at no extra cost. Used as a reward inside the GEPA prompt optimizer, Object Aligner helps or stays neutral across all datasets.
作者Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan
Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains spanning topical and security prompts, kNNGuard achieves competitive or superior F1 compared to fine-tuned state-of-the-art guardrails while running 2.7x faster than the best comparable guardrail, and 10x faster than a fine-tuned safety classifier without gradient updates or fine-tuning. Domain adaptation requires only updating the labeled bank, which can be constructed in under 10 seconds and several orders of magnitude faster than established guardrails. We also analyze the impact of system prompts, layer selection, and integration into production LLM pipelines as a configurable, low-latency guardrail.
展开完整摘要收起摘要↓
Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains spanning topical and security prompts, kNNGuard achieves competitive or superior F1 compared to fine-tuned state-of-the-art guardrails while running 2.7x faster than the best comparable guardrail, and 10x faster than a fine-tuned safety classifier without gradient updates or fine-tuning. Domain adaptation requires only updating the labeled bank, which can be constructed in under 10 seconds and several orders of magnitude faster than established guardrails. We also analyze the impact of system prompts, layer selection, and integration into production LLM pipelines as a configurable, low-latency guardrail.
作者Hamed Babaei Giglou, Jennifer D'Souza, Andrei Aioanei, Nandana Mihindukulasooriya, Sören Auer
Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, and evaluation practices. Despite decades of research, OL lacks a shared infrastructure for systematic evaluation and ontology access. This absence has hindered progress and fragmented research, leaving the central challenges of OL largely unaddressed. We introduce OntoLearner, a modular, cross-domain, and first-of-its-kind framework that unifies ontology access, large language model (LLM)-driven learning pipelines, and standardized benchmarking. OntoLearner releases 180 machine-readable ontologies spanning 22 domains and provides pipeline-ready datasets with train/dev/test splits for three core OL tasks: term typing, taxonomy discovery, and non-taxonomic relation extraction. Using this infrastructure, we conduct a large-scale empirical study of OL, evaluating 22 retrieval models and 12 LLMs across domains and tasks. The results converge on a finding that reframes the central challenge of OL: failure modes scale with ontological complexity rather than model size or architectural sophistication. The primary bottleneck is not model capability, but a structural mismatch between how models encode knowledge and how ontologies organize it. These findings establish that effective OL is reachable through the cross-domain, multi-task benchmarking enabled by OntoLearner. OntoLearner is open-source (MIT license) at https://github.com/sciknoworg/OntoLearner/.
展开完整摘要收起摘要↓
Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, and evaluation practices. Despite decades of research, OL lacks a shared infrastructure for systematic evaluation and ontology access. This absence has hindered progress and fragmented research, leaving the central challenges of OL largely unaddressed. We introduce OntoLearner, a modular, cross-domain, and first-of-its-kind framework that unifies ontology access, large language model (LLM)-driven learning pipelines, and standardized benchmarking. OntoLearner releases 180 machine-readable ontologies spanning 22 domains and provides pipeline-ready datasets with train/dev/test splits for three core OL tasks: term typing, taxonomy discovery, and non-taxonomic relation extraction. Using this infrastructure, we conduct a large-scale empirical study of OL, evaluating 22 retrieval models and 12 LLMs across domains and tasks. The results converge on a finding that reframes the central challenge of OL: failure modes scale with ontological complexity rather than model size or architectural sophistication. The primary bottleneck is not model capability, but a structural mismatch between how models encode knowledge and how ontologies organize it. These findings establish that effective OL is reachable through the cross-domain, multi-task benchmarking enabled by OntoLearner. OntoLearner is open-source (MIT license) at https://github.com/sciknoworg/OntoLearner/.
Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on reasoning models who produce long reasoning traces. By adapting the Recursive Feature Machine (RFM) algorithm — which can be computed efficiently — with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on reasoning (Qwen 3) and non-reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.
展开完整摘要收起摘要↓
Steering and monitoring activations in Large Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on reasoning models who produce long reasoning traces. By adapting the Recursive Feature Machine (RFM) algorithm — which can be computed efficiently — with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on reasoning (Qwen 3) and non-reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.
Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level semantic knowledge. Existing methods, however, largely treat semantics from large language models (LLMs) as auxiliary features or supervision, limiting their direct role in decision-making and constraining classification stability and robustness. To overcome this, we propose a semantic-aligned brain network framework that actively integrates LLM-derived semantics into the prediction process. Specifically, ROI-level semantics are first incorporated via global self-attention to enrich node representations and provide whole-brain context. Multi-scale hypergraphs are then constructed to explicitly model functional subnetworks and multi-ROI interactions, addressing the locality limitations of traditional GNNs and capturing high-order dependencies. Finally, a decision-level semantic alignment mechanism selectively injects patient-specific textual embeddings into graph representations, enabling semantics to directly guide predictions without perturbing the underlying network structure. Experiments on public brain network datasets ABIDE and ADHD-200 demonstrate state-of-the-art performance, enhanced stability, and improved interpretability, particularly in small-sample settings.
展开完整摘要收起摘要↓
Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level semantic knowledge. Existing methods, however, largely treat semantics from large language models (LLMs) as auxiliary features or supervision, limiting their direct role in decision-making and constraining classification stability and robustness. To overcome this, we propose a semantic-aligned brain network framework that actively integrates LLM-derived semantics into the prediction process. Specifically, ROI-level semantics are first incorporated via global self-attention to enrich node representations and provide whole-brain context. Multi-scale hypergraphs are then constructed to explicitly model functional subnetworks and multi-ROI interactions, addressing the locality limitations of traditional GNNs and capturing high-order dependencies. Finally, a decision-level semantic alignment mechanism selectively injects patient-specific textual embeddings into graph representations, enabling semantics to directly guide predictions without perturbing the underlying network structure. Experiments on public brain network datasets ABIDE and ADHD-200 demonstrate state-of-the-art performance, enhanced stability, and improved interpretability, particularly in small-sample settings.
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, and prior context, then injecting this information into future prompts. We study whether such memory reshapes reasoning on open-ended questions where no single ground-truth answer exists. To quantify this effect, we introduce DRIFTLENS, a ground-truth-free framework that maps each expressed reasoning step to a value category and measures divergence between a question's no-memory trajectory and its trajectory under injected user-attribute memory. We first validate that DRIFTLENS distinguishes content-free pragmatic noise from substantive reasoning changes. Across four LLMs and 10 user-attribute categories, including age, occupation, and disability, user-attribute memory induces medium-to-large reasoning drift above each model's pragmatic-noise floor, even when final answers remain fluent, on-topic, and plausible. We then evaluate GRPO- and DPO-based post-training methods for reducing drift. Both reduce drift, but neither uniformly dominates; effects on downstream capability, helpfulness, and instruction following are model-and reward-dependent. These results suggest that memory-induced reasoning drift is a measurable and only partly mitigated failure mode of personalized language models.
展开完整摘要收起摘要↓
Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, and prior context, then injecting this information into future prompts. We study whether such memory reshapes reasoning on open-ended questions where no single ground-truth answer exists. To quantify this effect, we introduce DRIFTLENS, a ground-truth-free framework that maps each expressed reasoning step to a value category and measures divergence between a question's no-memory trajectory and its trajectory under injected user-attribute memory. We first validate that DRIFTLENS distinguishes content-free pragmatic noise from substantive reasoning changes. Across four LLMs and 10 user-attribute categories, including age, occupation, and disability, user-attribute memory induces medium-to-large reasoning drift above each model's pragmatic-noise floor, even when final answers remain fluent, on-topic, and plausible. We then evaluate GRPO- and DPO-based post-training methods for reducing drift. Both reduce drift, but neither uniformly dominates; effects on downstream capability, helpfulness, and instruction following are model-and reward-dependent. These results suggest that memory-induced reasoning drift is a measurable and only partly mitigated failure mode of personalized language models.
作者Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei, Zhining Liu, Lingjie Chen, Ismini Lourentzou, Hanghang Tong, Jingrui He
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context Reasoning (RECONTEXT), a training-free inference method for improving long-context reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external memory, or context pruning. We also provide a theoretical analysis based on associative memory, which characterizes the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at https://github.com/Yanjun-Zhao/ReContext.
展开完整摘要收起摘要↓
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context Reasoning (RECONTEXT), a training-free inference method for improving long-context reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external memory, or context pruning. We also provide a theoretical analysis based on associative memory, which characterizes the context as a memory store, the question as a retrieval cue, attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at https://github.com/Yanjun-Zhao/ReContext.
作者Yongheng Zhang, Zhipeng Xu, Hao Wu, Yinghui Li, Di Yin, Xing Sun, Philip S. Yu
Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt "read-once, generate-many" paradigm, in which visual grounding weakens during generation. This phenomenon has been widely observed and is known as Visual Anchoring Decay. To fill this gap, we introduce Latent Video Cache (Latent-VC), a recurrent latent visual cache inserted into the decoder to preserve compact visual memories throughout reasoning. The cache is trained with supervised contrastive cache alignment and vision-grounded GRPO with a latent grounding reward, while maintaining strict train-inference alignment through native decoder hidden states. Built on Qwen3.5-9B, Latent-VC consistently outperforms strong CoT and SFT+GRPO baselines across six video benchmarks, with especially clear gains on grounding-intensive and long-video tasks. In addition, it also achieves higher accuracy with substantially shorter responses, suggesting that latent visual caching improves video reasoning by preserving visual evidence rather than relying on longer textual chains.
展开完整摘要收起摘要↓
Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt "read-once, generate-many" paradigm, in which visual grounding weakens during generation. This phenomenon has been widely observed and is known as Visual Anchoring Decay. To fill this gap, we introduce Latent Video Cache (Latent-VC), a recurrent latent visual cache inserted into the decoder to preserve compact visual memories throughout reasoning. The cache is trained with supervised contrastive cache alignment and vision-grounded GRPO with a latent grounding reward, while maintaining strict train-inference alignment through native decoder hidden states. Built on Qwen3.5-9B, Latent-VC consistently outperforms strong CoT and SFT+GRPO baselines across six video benchmarks, with especially clear gains on grounding-intensive and long-video tasks. In addition, it also achieves higher accuracy with substantially shorter responses, suggesting that latent visual caching improves video reasoning by preserving visual evidence rather than relying on longer textual chains.
We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon. Wiola introduces five independently novel components: (i) Spiral Rotary Positional Encoding (SRPE), which embeds token positions on a three-dimensional helical manifold combining absolute, relative, and hierarchical positional signals; (ii) Gated Cross-Layer Attention (GCLA), providing each decoder layer with soft cross-attention access to compressed summaries of two preceding layers for inter-layer coherence; (iii) Adaptive Token Merging (ATM), which dynamically merges se mantically redundant adjacent tokens in middle network layers to reduce attention complexity without information loss; (iv) Dual Stream Feed-Forward (DSFF), replacing the conventional MLP with two parallel streams fused by a learned per-dimension gate; and (v) WiolaRMSNorm, a modified normalisation introducing a per-dimension learned offset vector that prevents representation collapse. We provide complete mathematical derivations, architectural block diagrams, complexity analyses, and systematic comparisons against GPT-2, LLaMA-2, and Mistral. Wiola is released in four sizes (120M, 360M, 700M, and 1.5B parameters) and is fully compatible with the HuggingFace Transformers ecosystem, with all 22 architectural unit tests passing.
展开完整摘要收起摘要↓
We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon. Wiola introduces five independently novel components: (i) Spiral Rotary Positional Encoding (SRPE), which embeds token positions on a three-dimensional helical manifold combining absolute, relative, and hierarchical positional signals; (ii) Gated Cross-Layer Attention (GCLA), providing each decoder layer with soft cross-attention access to compressed summaries of two preceding layers for inter-layer coherence; (iii) Adaptive Token Merging (ATM), which dynamically merges se mantically redundant adjacent tokens in middle network layers to reduce attention complexity without information loss; (iv) Dual Stream Feed-Forward (DSFF), replacing the conventional MLP with two parallel streams fused by a learned per-dimension gate; and (v) WiolaRMSNorm, a modified normalisation introducing a per-dimension learned offset vector that prevents representation collapse. We provide complete mathematical derivations, architectural block diagrams, complexity analyses, and systematic comparisons against GPT-2, LLaMA-2, and Mistral. Wiola is released in four sizes (120M, 360M, 700M, and 1.5B parameters) and is fully compatible with the HuggingFace Transformers ecosystem, with all 22 architectural unit tests passing.
Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors to overlap, and the generated responses may fail to effectively align with the corresponding preference vectors. In this paper, we propose Multi-Objective Exploration and Preference Optimization via Mutual Information (MI-EPO), an information-theoretic framework. It unifies multi-objective exploration and alignment by maximizing the joint conditional mutual information among generated responses, preference feedback, and preference vectors. By incorporating a probabilistic routing mechanism, MI-EPO naturally decomposes objective alignment and preference-aware exploration, encouraging the model to generate responses that are distinguishable and aligned with different preference conditions. Experiments on safe alignment and helpful assistant tasks show that MI-EPO significantly improves the alignment between generated responses and preference vectors, makes the outputs more controllable, and achieves stable trade-offs across multiple objectives.
展开完整摘要收起摘要↓
Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors to overlap, and the generated responses may fail to effectively align with the corresponding preference vectors. In this paper, we propose Multi-Objective Exploration and Preference Optimization via Mutual Information (MI-EPO), an information-theoretic framework. It unifies multi-objective exploration and alignment by maximizing the joint conditional mutual information among generated responses, preference feedback, and preference vectors. By incorporating a probabilistic routing mechanism, MI-EPO naturally decomposes objective alignment and preference-aware exploration, encouraging the model to generate responses that are distinguishable and aligned with different preference conditions. Experiments on safe alignment and helpful assistant tasks show that MI-EPO significantly improves the alignment between generated responses and preference vectors, makes the outputs more controllable, and achieves stable trade-offs across multiple objectives.
At the heart of human visual perception lies the ability to maintain a continuous and coherent understanding of the external world. By integrating observations with accumulated experience, the human visual system can continuously adapt to variations in both the target and its surrounding environment, while preserving robust visual continuity as scene dynamics evolve. Human vision can therefore integrate prior knowledge, spatial geometry, and semantic context to understand complex scenes and their changes. As a core problem in computer vision, visual object tracking aims to bring machine perception closer to human visual perception. These capabilities are central to the task of Generic Object Tracking (GOT). In this task, a visual tracker is initialized only with the bounding box of an arbitrarily specified target in the first frame, and must continuously localize the target in subsequent dynamic visual streams. However, future events, observations, and real-world variations are inherently unpredictable; therefore, the model's generalization and online adaptation capabilities remain bottlenecks. Tracking reliability can deteriorate when the target undergoes severe deformation, is affected by complex distractors, encounters significant environmental changes, or belongs to a category unseen during training. This dissertation aims to narrow the gap between machine visual tracking systems and human visual perception by proposing a series of methods that systematically enhance the target discrimination, robust adaptation, and geometric reasoning capabilities of tracking models.
展开完整摘要收起摘要↓
At the heart of human visual perception lies the ability to maintain a continuous and coherent understanding of the external world. By integrating observations with accumulated experience, the human visual system can continuously adapt to variations in both the target and its surrounding environment, while preserving robust visual continuity as scene dynamics evolve. Human vision can therefore integrate prior knowledge, spatial geometry, and semantic context to understand complex scenes and their changes. As a core problem in computer vision, visual object tracking aims to bring machine perception closer to human visual perception. These capabilities are central to the task of Generic Object Tracking (GOT). In this task, a visual tracker is initialized only with the bounding box of an arbitrarily specified target in the first frame, and must continuously localize the target in subsequent dynamic visual streams. However, future events, observations, and real-world variations are inherently unpredictable; therefore, the model's generalization and online adaptation capabilities remain bottlenecks. Tracking reliability can deteriorate when the target undergoes severe deformation, is affected by complex distractors, encounters significant environmental changes, or belongs to a category unseen during training. This dissertation aims to narrow the gap between machine visual tracking systems and human visual perception by proposing a series of methods that systematically enhance the target discrimination, robust adaptation, and geometric reasoning capabilities of tracking models.
作者Md Mohasin Hossain, Anar Amirli, Robert Leist, Md Abdul Kadir, Daniel Sonntag
Concept Bottleneck Models (CBMs) provide an intrinsically interpretable alternative to post-hoc explanations. However, existing CBMs often rely on predefined concept vocabularies or supervised annotations, lack explicit concept grounding, and summarize each concept with a single image-level score — discarding spatial recurrence and inter-concept dependencies. We propose a Graph-based Concept Bottleneck Model (G-CBM), an intrinsically interpretable framework that performs unsupervised concept discovery via Non-negative Matrix Factorization (NMF) and represents the discovered concepts as nodes in a per-image concept-graph representation. G-CBM matches region-level features to these concept nodes — providing concept grounding and capturing concept recurrence across the image — and applies a tunable concept filtering threshold $τ$ to suppress weak region-level features. A Graph Attention Network (GAT) then performs concept-level reasoning by modeling nonlinear dependencies across nodes. Across ImageNet, HAM10000, PH2, and Derm7pt, G-CBM achieves an average relative AUC improvement of 3.7% over a ResNet-50 baseline. Concept filtering frequently improves predictive performance while inducing selective concept use, achieving peak AUC of $0.96$ on PH2 with only 2 of 10 concepts and 0.92 on HAM10000 with 3.8 of 9 concepts. On dermoscopy benchmarks, G-CBM is competitive with supervised approaches requiring external annotations. Deletion/insertion analyses with random ablation controls show that the learned concept ranking faithfully reflects model predictions.
展开完整摘要收起摘要↓
Concept Bottleneck Models (CBMs) provide an intrinsically interpretable alternative to post-hoc explanations. However, existing CBMs often rely on predefined concept vocabularies or supervised annotations, lack explicit concept grounding, and summarize each concept with a single image-level score — discarding spatial recurrence and inter-concept dependencies. We propose a Graph-based Concept Bottleneck Model (G-CBM), an intrinsically interpretable framework that performs unsupervised concept discovery via Non-negative Matrix Factorization (NMF) and represents the discovered concepts as nodes in a per-image concept-graph representation. G-CBM matches region-level features to these concept nodes — providing concept grounding and capturing concept recurrence across the image — and applies a tunable concept filtering threshold $τ$ to suppress weak region-level features. A Graph Attention Network (GAT) then performs concept-level reasoning by modeling nonlinear dependencies across nodes. Across ImageNet, HAM10000, PH2, and Derm7pt, G-CBM achieves an average relative AUC improvement of 3.7% over a ResNet-50 baseline. Concept filtering frequently improves predictive performance while inducing selective concept use, achieving peak AUC of $0.96$ on PH2 with only 2 of 10 concepts and 0.92 on HAM10000 with 3.8 of 9 concepts. On dermoscopy benchmarks, G-CBM is competitive with supervised approaches requiring external annotations. Deletion/insertion analyses with random ablation controls show that the learned concept ranking faithfully reflects model predictions.
We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback overexisting rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0
展开完整摘要收起摘要↓
We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback overexisting rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0
作者Samuel Schapiro, Core Francisco Park, Felix Sosa, Lav R. Varshney
Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what has been termed the artificial hivemind effect. Here, we introduce CreativityNeuro, a data-free method for enhancing divergent thinking in LLMs via contrastive weight steering. We evaluate our method across multiple creativity assessments and report several main findings. On the Divergent Association Task (DAT), a vocabulary-space creativity test, CreativityNeuro improves performance by up to 14 human percentile points. Next, in a large-scale human evaluation (N=720) on the Alternative Uses Test (AUT) and the Task Task, CreativityNeuro achieves significant improvements in originality, surprise, and creativity, transferring to longer-form and more open-ended tasks. Importantly, we find that across all three tasks, CreativityNeuro demonstrably reduces measures of mode collapse. Moreover, activation steering achieves comparable performance to CreativityNeuro on the DAT, but it does not transfer to the AUT and Task Task, demonstrating the effectiveness of weight-space steering in generalizing to unseen tasks. In conclusion, CreativityNeuro improves divergent thinking and reduces mode collapse without requiring behavioral data, re-training, or gradient-based fine-tuning, providing a straightforward way to enhance LLM performance in creative domains.
展开完整摘要收起摘要↓
Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what has been termed the artificial hivemind effect. Here, we introduce CreativityNeuro, a data-free method for enhancing divergent thinking in LLMs via contrastive weight steering. We evaluate our method across multiple creativity assessments and report several main findings. On the Divergent Association Task (DAT), a vocabulary-space creativity test, CreativityNeuro improves performance by up to 14 human percentile points. Next, in a large-scale human evaluation (N=720) on the Alternative Uses Test (AUT) and the Task Task, CreativityNeuro achieves significant improvements in originality, surprise, and creativity, transferring to longer-form and more open-ended tasks. Importantly, we find that across all three tasks, CreativityNeuro demonstrably reduces measures of mode collapse. Moreover, activation steering achieves comparable performance to CreativityNeuro on the DAT, but it does not transfer to the AUT and Task Task, demonstrating the effectiveness of weight-space steering in generalizing to unseen tasks. In conclusion, CreativityNeuro improves divergent thinking and reduces mode collapse without requiring behavioral data, re-training, or gradient-based fine-tuning, providing a straightforward way to enhance LLM performance in creative domains.
作者Siddharth Gollapudi, Nilesh Gupta, Prasann Singhal, Sewon Min
Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant answer. However, prior work has largely focused on proprietary systems or the smaller-scale reranking task, leaving corpus-scale in-context retrieval largely unexplored. In this work, we present the first systematic study of in-context retrieval on two scales practical retrievers demand: million-token corpora and length-generalization far beyond training-time sizes. We first introduce BlockSearch, a 0.6B LM retriever whose architectural and training modifications improve over prior LM baselines and length-generalize up to 10 times beyond its training regime. Nevertheless, retrieval still collapses under more extreme extrapolation. We trace this failure to an attention dilution effect: as the corpus grows, irrelevant documents dominate the softmax denominator, reducing the normalized mass on the gold document even when its pre-softmax score stays high. Motivated by this analysis, we introduce length-aware adjustments to the attention softmax and document-level sparse attention. With these modifications, at the million-token scale, our model matches dense retrieval on widely studied benchmarks (e.g, MS MARCO and NQ), while outperforming the concurrent model MSA despite being 7 times smaller. Furthermore, it significantly outperforms dense retrieval on tasks requiring entirely different notions of similarity, such as LIMIT, achieving a 3 times higher score. Together, our results position in-context retrieval a promising alternative to classical retrieval while emphasizing attention control under extreme context growth as a new challenge.
展开完整摘要收起摘要↓
Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant answer. However, prior work has largely focused on proprietary systems or the smaller-scale reranking task, leaving corpus-scale in-context retrieval largely unexplored. In this work, we present the first systematic study of in-context retrieval on two scales practical retrievers demand: million-token corpora and length-generalization far beyond training-time sizes. We first introduce BlockSearch, a 0.6B LM retriever whose architectural and training modifications improve over prior LM baselines and length-generalize up to 10 times beyond its training regime. Nevertheless, retrieval still collapses under more extreme extrapolation. We trace this failure to an attention dilution effect: as the corpus grows, irrelevant documents dominate the softmax denominator, reducing the normalized mass on the gold document even when its pre-softmax score stays high. Motivated by this analysis, we introduce length-aware adjustments to the attention softmax and document-level sparse attention. With these modifications, at the million-token scale, our model matches dense retrieval on widely studied benchmarks (e.g, MS MARCO and NQ), while outperforming the concurrent model MSA despite being 7 times smaller. Furthermore, it significantly outperforms dense retrieval on tasks requiring entirely different notions of similarity, such as LIMIT, achieving a 3 times higher score. Together, our results position in-context retrieval a promising alternative to classical retrieval while emphasizing attention control under extreme context growth as a new challenge.
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-time prompts, while the generated reasoning traces are rarely reused as semi-supervised learning signals. In this report, we define Semi-supervised Chain-of-Thought Learning and propose Semi-CoT, a simple framework that uses unlabeled questions to construct pseudo reasoning supervision. Semi-CoT samples multiple pseudo-CoTs for each unlabeled question, estimates answer-level semantic entropy, and selects low-entropy reasoning chains as reliable pseudo-CoT demonstrations. This extends the self-training view of CoT from inference-time refinement to semi-supervised pseudo-supervision. Pilot experiments on AQuA, SVAMP, GSM8K, and MultiArith show that the entropy gate selects high-precision pseudo-CoTs, with pseudo-answer precision ranging from $91.36%$ to $100%$. Semi-CoT also gives small gains on SVAMP and GSM8K, while AQuA shows negative transfer and MultiArith reaches a ceiling. These results suggest that unlabeled questions can provide reliable pseudo reasoning signals, but their effective use still requires stronger demonstration selection or student training.
展开完整摘要收起摘要↓
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-time prompts, while the generated reasoning traces are rarely reused as semi-supervised learning signals. In this report, we define Semi-supervised Chain-of-Thought Learning and propose Semi-CoT, a simple framework that uses unlabeled questions to construct pseudo reasoning supervision. Semi-CoT samples multiple pseudo-CoTs for each unlabeled question, estimates answer-level semantic entropy, and selects low-entropy reasoning chains as reliable pseudo-CoT demonstrations. This extends the self-training view of CoT from inference-time refinement to semi-supervised pseudo-supervision. Pilot experiments on AQuA, SVAMP, GSM8K, and MultiArith show that the entropy gate selects high-precision pseudo-CoTs, with pseudo-answer precision ranging from $91.36%$ to $100%$. Semi-CoT also gives small gains on SVAMP and GSM8K, while AQuA shows negative transfer and MultiArith reaches a ceiling. These results suggest that unlabeled questions can provide reliable pseudo reasoning signals, but their effective use still requires stronger demonstration selection or student training.