LLM 理论进展

Large language models (LLMs) show strong reasoning ability, but their explanations can remain inconsistent, weakly grounded, or difficult to verify. We propose a verifier-guided explainable reasoning framework for transparent educational question answering that combines gold-anchored QLoRA, task-aware symbolic routing, and group-relative RLVR. Qwen2.5-3B-Instruct is first adapted with field-weighted QLoRA supervision anchored to authoritative answers. A lightweight router then assigns logic problems to a FOL/Z3 verifier and physics problems to a formula- and unit aware symbolic solver. Verifier feedback is further used to support candidate evaluation, self-revision, and reward construction during RLVR. Candidate responses are evaluated along three complementary dimensions: P1 for answer correctness, P2 for evidence or unit consistency, and P3 for reasoning depth and explainability. At inference, gold-free self-consistency aggregates multiple candidate responses before an optional question-only physics verifier performs conservative system-level correction. On 438 held-out examples, RLVR increases P3 from 50.68% to 72.20%, while hybrid P1 remains approximately stable at 55.94%. Self-consistency improves model only P1 from 48.86% to 50.23%, with symbolic verification providing the remaining hybrid gain. These results indicate that RLVR primarily strengthens explicit reasoning structure, while symbolic verification complements the neural policy by improving answer reliability at the system level.

Human knowledge is inherently structured and interdependent: mastery of a concept requires prior mastery of its prerequisites, a principle formalized by Knowledge Space Theory (KST). While LLMs achieve strong performance on complex reasoning tasks, it remains unclear whether they exhibit coherent, human-like knowledge structure. We introduce a KST-grounded framework for evaluating LLM knowledge structure in mathematical reasoning, using it as a normative framework to analyze whether LLM behavior adheres to principled knowledge dependencies. Evaluating eight open- and closed-source LLMs against real human learners, we find that (1) LLMs do not adhere to human knowledge structure — they frequently violate knowledge dependencies and fail to leverage related knowledge provided in context to improve performance on dependent questions; (2) LLMs do not share a consistent knowledge structure among themselves, as reflected by low overlap in their knowledge distributions. Furthermore, these structural deficiencies remain largely invisible to accuracy-based and LLM-as-judge evaluations. Together, our results provide behavioral evidence that current LLMs knowledge does not follow a human-like structure.

A transformer language model assigns a single, context-independent vector to a word type at its embedding layer, yet is widely believed to individuate that word's occurrences by context in its later layers. Testing this belief cleanly requires a construct that holds the word form fixed while its context and intended sense vary in a controlled, labeled way. This manual documents an open toolkit built around such a construct, which we call a bridge form: a single written word that recurs, unchanged, across two or more subject domains with a different sense in each. We describe, and justify, every stage of the pipeline: the declarative specification of bridge forms and their source domains, corpus acquisition from Wikipedia, occurrence localization, layer-wise representation extraction, a domain-pairwise silhouette measurement of separation in the model's representation space, and a paired visualization protocol. Each design choice is presented together with the methodological failure mode it is meant to avoid (sense contamination from overly broad category labels, the multi-group bias of the silhouette coefficient, subword-tokenization misalignment, and axis-comparability artifacts in dimensionality-reduced plots, among others). This manuscript is a methodological and implementation reference: it does not report or interpret empirical outcomes of running the toolkit on any particular model or bridge-form set. The toolkit, its full source, and the corpora used to exercise it are archived separately (Section 9) under a persistent identifier, and are intended to be cited as an instrument by studies that use it to produce and interpret empirical results.

Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling, which induces three fundamental defects in complex logical reasoning: error accumulation, probability substituting necessity, and the linear-chain information bottleneck. This paper proposes the Deterministic Operator-Driven Reasoning in Latent Space architecture (DODR), which reconstructs reasoning as reasoning-graph computation in a high-dimensional linear-algebraic space. Reasoning states are represented as snapshot vectors whose primitives are semantic units (phrases or sentences) rather than tokens, and each inference step is a deterministic matrix operation with no token sampling. Peirce's three inference types are formalized as three trainable matrix operators: a rank-deficient deduction operator (information collapse), a full-rank induction operator (information expansion), and an abduction operator defined as the Moore-Penrose pseudo-inverse of deduction (information hypothesizing). We prove that the operator set is minimal and complete given Peirce's trichotomy, that no single "super-operator" can realize all three types (a rank obstruction), and that reasoning graphs are Turing-complete with contractive backflow converging by Banach's fixed-point theorem. Experiments on 503 sample records (420 deduplicated samples) across dedicated and end-to-end settings show: deduction loss converges to 1.40e-05; induction achieves 0.9996 generalization coverage with 20/20 hard vetoes on counterexamples; abduction solutions exceed the random baseline by 28x with judgment accuracies of 72.5% (58/80, Wilson 95% CI [61.9%, 81.1%]) and 81.7% (49/60, CI [70.1%, 89.4%]); frozen operators attain 100% (60/60) on unseen cross-domain deduction. The architecture provides a structural zero-hallucination guarantee and a three-layer continual-learning mechanism. All data and code are released.

Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large language models (LLMs). Time-to-first-spike (TTFS) coding generates at most one spike per neuron within a time window, yielding extremely low firing rates. However, conventional TTFS SNNs are restricted to specific structures, making it challenging to encode certain blocks in LLM — such as layer normalization and matrix multiplication --using TTFS. To overcome this limitation, we introduce a reference-based strategy specifically to encode the four core LLM components: embedding layers, layer normalization, attention-related operations and dropout. We construct a fully TTFS-based SNN architecture and train it end-to-end. Experiments on modern LLMs like BERT and GPT-2 demonstrate that our approach achieves performance comparable to ANN counterparts on natural language understanding and common-sense reasoning, while a clear gap remains on language modeling perplexity. To the best of our knowledge, this is the first work to scale a spiking LLM to 1.5 billion parameters using TTFS coding. We also report an estimate of spike-related energy; this is a spike-count proxy under an established cost model rather than a measurement on neuromorphic hardware.

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are explicitly distinguished in text, little is known about how they are geometrically organized in representation spaces. To this end, we investigate whether distinct reasoning operations exhibit corresponding geometric structure in hidden representations. We find that operations are separable in held-out representations, with separability peaking in middle layers, and verify that this structure is not explained by lexical or positional confounds. Across layers, token-wise operation-alignment becomes more distributed over spans, while identical surface tokens are represented differently depending on the operation of its surrounding chunk. Attention-masking interventions further show that operation-aligned representations at chunk onset depend on preceding reasoning context. Consequently, our work demonstrates that language models maintain representational correspondence between linguistic reasoning expressions and their internal geometric structures. Code and project materials are available at https://github.com/naver-ai/beneath-cot.

Large language models (LLMs) are increasingly used not only to retrieve information, but to answer questions, explain, teach, and support inquiry. In such settings, evaluation cannot be exhausted by accuracy or alignment alone. A system may give a correct answer while still narrowing users' access %to knowledge. to alternative valid answers, explanations, or reasoning routes. Drawing on the broader notion of epistemic diversity in philosophy and social epistemology, we formalize it in the context of LLMs as the range of valid answers, explanations, and reasoning routes that an LLM exposes to users. We argue that epistemic diversity is a useful evaluation dimension for settings where LLMs are used to support knowledge-intensive tasks. We propose a preliminary framework for conceptualizing and measuring epistemic diversity in LLMs, and operationalize it in two domains. We find that frontier LLMs often exhibit epistemic narrowness, repeatedly collapsing large valid answer spaces onto small canonical subsets. These findings suggest that LLM evaluation should move beyond accuracy-oriented paradigms and treat epistemic diversity as an important dimension of model capability.

In many forms of reasoning, including arithmetic reasoning, generalizing across superficial changes in input format is effortless for humans: anyone who can solve 2+5 can also solve 'two plus five'. In contrast, LLMs are more brittle to surface variations of the prompts: for example, they solve numeric arithmetic problems almost perfectly but are substantially less accurate on verbal renditions of the same problems. Here, we ask whether generalization across formats can be predicted from the models' internals. Using attribution patching, we first independently localize the circuit that each model recruits to solve numeric arithmetic problems (2+5) vs. verbal ones, in three languages: English ('two plus five'), Spanish ('dos más cinco'), and Italian ('due più cinque'); then, we test whether overlap with the model's own numeric circuit predicts its generalization to the verbal formats. Indeed, we find support for this idea at three levels: circuit overlap accounts for the relative difficulty of the three verbal formats, for which models generalize best, and for which items are solved correctly, rivaling supervised probes while requiring no labeled data.

This paper investigates structural priming in language model (LM) production, examining how preceding structural context influences sentence completion. While prior work has demonstrated priming effects in comprehension of structural alternations, it remained unclear whether these persist in production, where, when generating, an LM samples from many possible continuations at each step. We address this question through a series of controlled sentence-completion experiments on dative constructions. In line with prior work, we find that LMs are susceptible to structural priming, particularly in sentences that are semantically coherent. In terms of priming magnitude, we find that while there is a greater relative increase of double-object datives against our baselines, in line with inverse frequency effects, there is a larger absolute increase in prepositional-objects, the more frequently produced construction. Finally, we not only observe that structural priming is boosted by lexico-semantic coherence, but that structurally primed completions display greater levels of lexico-semantic repetition. Taken together, our evidence supports the view that structural priming in LMs operates across multiple levels of linguistic representation, facilitating, and facilitated by syntactic, lexical, and semantic alignment. Code: https://github.com/the-context-lab/primedproduction.

Large language models (LLMs) are increasingly used to annotate cultural texts at scales that are impractical for human coders. However, before their outputs are treated as measurements of latent social constructs, it is necessary to establish whether those measurements are reliable. This study evaluates five LLMs as zero-shot annotators of four social constructs expressed in English song lyrics: self-esteem, self-control, seeking belonging, and seeking recognition. Using repeated annotations of a large lyric corpus, we examine three properties of LLM-based measurement: consistency across repeated runs, convergence across models, and transferability of consensus labels to supervised classification. The findings show that LLM-based measurement is not uniformly reliable across constructs. Self-esteem exhibits the strongest repeated-measurement reliability across models, while seeking recognition is generally less stable; self-control and seeking belonging show intermediate but model-dependent reliability. Downstream classification further indicates that consensus LLM labels contain learnable signal, although transferability does not itself establish construct validity. Repeated-measurement stability and cross-model convergence should therefore be reported before LLM annotations are treated as scalable measurements in cultural analytics.

Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior. Unfortunately, these explanations can be unfaithful, failing to reflect the actual reasoning underlying the model's decisions. We consider a setting in which an LLM provides both an answer and an explanation in response to a question. We identify two distinct dimensions of unfaithful explanations: incompleteness, meaning that the explanation omits factors that influence the answer, and unsoundness, meaning that the explanation cites factors that did not influence the model's answer. Existing approaches to improving LLM faithfulness include training-time methods, which require access to model weights and extensive computational resources, and test-time methods that largely focus on addressing unsoundness. We introduce a test-time approach that directly targets incompleteness. We remove from the input the concepts not credited in the model's explanation and re-query the model on the reduced input. This eliminates unmentioned influences while preserving the influence of mentioned concepts. Across two datasets, multiple model families, and two independent faithfulness metrics, our approach improves explanation faithfulness compared to both standard prompting and prompting to encourage faithfulness. Our method is model-agnostic and can be applied at inference time without modifying model parameters, providing a flexible mechanism for reducing hidden influences and improving the reliability and safety of LLM-assisted decision making.

Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants. Different developers may prefer different models, and individual developers may switch between models across different coding sessions. Because of this, the edits any one model makes are frequently applied to foreign code originally generated by another model. These LLMs are often trained on different datasets, and as a result have different stylistic preferences. Do LLMs behave differently when they edit foreign code originally written by a different LLM with a different coding style? We find that models tend to make more, and often excessive, edits on foreign code. We introduce CROCODIL (Cross-model Code Editing with LLMs), a post-training framework for reducing excessive edits while preserving functional correctness. CROCODIL's similarity reward penalizes large changes, while its execution reward scores build and test success. We use the product of these two rewards to encourage the policy to decrease the edit size without decreasing the edit task success rate. CROCODIL is available at https://github.com/EngineeringSoftware/Crocodil.

Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationally tractable. Existing feed-forward reconstruction methods are inherently limited to content visible in the input images, while 3D generative modeling is hindered by the high computational cost of dense volumetric representations and the scarcity of large-scale 3D supervision. We introduce SPAR3S, a sparse voxel-aligned 3D latent generative model for conditional scene completion without requiring ground-truth 3D data for supervision. Our key insight is to formulate 3D scene generation in a structured, compact, voxel-aligned 3D latent space where only occupied voxels are represented. We learn this sparse latent space directly from multi-view images using photometric supervision via differentiable 3D Gaussian Splatting. Given a partial set of observed voxels encoded from sparse input views, scene completion reduces to predicting the missing latent tokens and their spatial support within the voxel grid. To this end, we train a masked autoregressive transformer that jointly models voxel occupancy and latent token values, enabling efficient and spatially consistent generation of unseen regions. We demonstrate the effectiveness of our method on synthetic indoor scenes, achieving higher novel-view quality than prior work. We further validate its generalization on RealEstate10k, highlighting its applicability to real-world data.

Repeating a small block of middle layers increases a language model's effective inference depth without adding parameters or generating extra tokens, and recent work shows that this latent recurrence improves reasoning. However, two design choices limit these gains. Each iteration sees only the previous output and cannot directly access earlier computations. Moreover, a fixed loop count wastes depth on easy inputs while leaving hard ones with too little computation. We introduce RecurTrace, which addresses both limitations using the loop's own trajectory. Specifically, Loop Memory Attention lets each looped layer attend to its own states from previous iterations along the loop-time axis, so the model can revisit earlier computations instead of relying on the latest state alone. A halting head then reads the loop state and predicts whether to continue, with supervision from an oracle that identifies when additional depth still reduces loss. In a controlled MathQA comparison on the same looped backbone, RecurTrace achieves 56.9% accuracy with an average of 2.0 loops, exceeding the best fixed loop depth by 2.2 points at matched compute. By comparison, ACT and PonderNet collapse to one loop, and CALM reaches only 54.1% with 5.6 loops, while the stronger LoopUS-Conf and TaH-Mismatch baselines reach 55.3% at 3.2 loops and 55.7% at 2.1 loops. Finally, RecurTrace improves generation accuracy over same-budget fine-tuned baselines at 0.6B, 1.7B, 4B, and 8B, with the gain growing with model size from 0.6 to 3.4 points.

Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-free early-exit methods shorten these traces by choosing an intermediate point to stop reasoning. We study one such strategy that injects an end-of-think token (EoT, </think>) at this point to trigger the reasoning-to-answering transition, and find that the injected EoT does not always induce a clean answering phase. Answering-phase generation can continue before the model regenerates another EoT, with the span preceding this regenerated EoT scaling with the reasoning tokens saved by early exit and exhibiting continued reasoning behavior. We call this spurious CoT termination, where reasoning-like generation continues into the answering phase. We hypothesize that insufficient attention to the injected EoT contributes to spurious CoT termination and probe this hypothesis with Exit-token Attention Biasing (EAB). Across four LRMs, five benchmarks, and two early-exit methods, increasing attention to the injected EoT reduces spurious CoT termination and answering-phase length. These results reveal a limitation of controlling LRMs by externally matching their explicit think-block format. Inserting the EoT token conforms to this format but does not by itself guarantee the intended reasoning-to-answering transition. Our code is available at https://github.com/Seunghee-Koh/Spurious-CoT-Termination.

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training on reasoning chains that justify a safety decision), and preference optimization (ORPO) - across three architecturally distinct models (Llama-3.1-8B, Gemma-2-9B, Qwen3-8B). We find that training method, not just data, reshapes how refusal is computed internally: reasoning-augmented training consistently produces a distinct kind of refusal computation, visible across all three models, while architecture independently shapes internal structure and how reliably refusal can be steered. Most importantly, no method we study achieves all three properties we would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits. We caution against treating current post-training methods as a solved, reliable defense, especially for security-critical use. Code and models are available in https://github.com/hoangcuongnguyen2001/Beyond-Shallow-Alignment.

Coreference resolution is an important task in contextual reasoning. In this paper, we investigate the mechanism for representing and retrieving singular and plural entities for plural reference. We use a combination of mechanistic interpretability and attention pattern analysis to study the process in which LLMs predict a pronoun to refer back to previously mentioned entities. Using a range of causal intervention techniques, we find a set of attention heads that are responsible for (1) representing coreference information in the input, (2) identifying entities that form a plural reference, (3) transferring the information to the component that is responsible for selecting the antecedents and predicting the pronoun. We also find that LLMs align with humans in preference for plural pronoun. Specifically, entities in a plural construction are more likely to be referred to as a plural entity if they are ontologically similar and are linked by the conjunction "and".

Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented explicitly, and are often hidden inside source code commits. Recovering them is important for Architectural Knowledge Management (AKM). Problem: Extracting ADDs from commits is challenging due to their implicit and unstructured nature. Large Language Models (LLMs) have shown strong capabilities in understanding code and text, yet their effectiveness for this task remains underexplored. Study: We present a preliminary study using four LLMs (Gemini 3 Pro, DeepSeek R1, Kimi K2, Qwen3) with zeroshot and fewshot prompting on 30 developer-written ADDs from open-source projects. We score outputs with ROUGE-L, BLEU, METEOR, and BERTScore, and one author manually reviews the Gemini outputs. Results: All models reach a BERT-F1 above 0.81, and fewshot prompting improves alignment (Gemini BERT-F1: 0.828 to 0.847). However, the generated ADDs are often too long, implementation-focused, and miss the rationale behind the decision. This highlights opportunities for architecture-aware LLM systems and automated AKM.

Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.

Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-relevant evidence as additional visual context. Though effective, this store-and-retrieve paradigm keeps historical evidence as external visual context, preventing it from being internalized into a compact, evolving latent memory that can continuously guide streaming reasoning. To bridge this gap, we introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize. Specifically, LatentStream comprises three coordinated components. First, Query-agnostic Hierarchical Streaming Memory organizes visual history into short-, mid-, and long-term levels under a fixed memory budget through Jenks-guided adaptive consolidation. Once a query arrives, Hierarchical Latent Memory Evolution equips groups of latent memory tokens with progressively expanding memory receptive fields, enabling them to iteratively retrieve historical evidence from their corresponding scopes and internalize it into a compact, fixed-length latent memory. Finally, Progressive Confidence-guided Latent Memory Optimization constructs a hierarchical progression reward from group-wise predictive entropy and jointly refines the latent memory tokens and retrieved evidence, encouraging increasingly confident streaming reasoning. Extensive experiments demonstrate that LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.

Language models encounter typos, corrupted text, altered words, and disrupted token order, yet robustness is usually evaluated only through output behavior. We study how six naturalistic and synthetic input perturbations propagate through decoder-only language models at three levels: output behavior, hidden-state geometry, and attention-head function. We evaluate behavioral effects across four GPT-2 and two Qwen2.5 checkpoints by analyzing layerwise geometry using centered kernel alignment and intrinsic dimension, and examine attention-head responses in GPT-2. Perturbation types produce distinguishable metric profiles that are not fully captured by output measures and are only partly consistent across the tested checkpoints. Copying scores are especially associated with activation-patching recovery under token substitution and shuffling. Gradient-guided HotFlip perturbations also cause stronger behavioral and representational disruption than rate-matched random token substitutions in GPT-2; their behavioral effects are consistent across all six tested checkpoints. Our results show that robustness claims based on a single behavioral or representational metric can be misleading, and motivate multi-level evaluation of how perturbations alter language-model computation.

For trained operators, gauge reading requires little specialized knowledge, low cognitive effort, and high repeatability. Yet Multimodal Large Language Models (MLLMs) remain unreliable in continuous-valued measurement despite strong results on general multimodal benchmarks. Existing benchmarks expose this weakness but isolate measurement from realistic, knowledge-grounded settings, with limited situated context, specialized instruments, real-world noise, and matched diagnostic annotations, reducing realism and constraining root-cause analysis. We introduce InSituMeasure to evaluate situated measurement grounding. It contains 2,922 real industrial monitoring scenes across eight functional categories of professional engineering instruments, with dense gauge-attribute annotations and noise tags for failure diagnosis. We define metrics for numerical accuracy under predefined tolerances and unit consistency, rejection of fake or unanswerable tasks, and alignment between model failures and annotated error factors. Across 24 state-of-the-art MLLMs, the best model reaches only 25.7% joint value-unit accuracy and 51.8% confidence-diagnosis F1, revealing a substantial gap between general multimodal competence and reliable situated measurement. Further analysis identifies failures from text-induced shortcuts, overconfident responses, and authentic industrial noise, including mixed disturbances, viewpoint deviation, occlusion, and environmental interference.

Early screening of chronic kidney disease (CKD) is critical for timely intervention, yet most machine learning (ML) and deep learning (DL) approaches require labeled data and model training, limiting their use in real-world screening settings. This study evaluates the effectiveness of large language models (LLMs) for CKD screening under zero-shot and few-shot in-context learning settings and compares them with traditional ML and DL methods. We propose a framework that uses clinically selected tabular features and structured prompt templates to enable LLM-based inference without task-specific training. LLM performance is evaluated across multiple prompt styles, feature configurations, and data settings, and compared with standard ML, DL, and tabular foundation model (TFM) baselines, and existing CKD screening tools. The results show that LLMs can achieve competitive performance using only a small number of examples, often matching or outperforming traditional approaches in low-data settings. However, their performance remains model-dependent and less stable as input complexity increases. In contrast, ML, DL, and TFM models show more consistent improvement with larger training data. Overall, the findings highlight a trade-off between data efficiency and stability, suggesting that LLMs may serve as a flexible complementary approach for CKD screening when labeled data are limited. To facilitate further research and reproducibility, the code has been made publicly available at https://github.com/akabircs/LLM4CKD

Networks describe systems in biology and beyond, from protein interactions and social relationships to power grids and citation records. Reasoning about such systems requires understanding their structure: which elements are central, which connections bridge separate communities, and how it changes when elements are removed. Although large language models (LLMs) excel at natural language, they struggle with such questions when networks are given as edge lists, sentences or measurement tables, because their structural meaning must be inferred. Here we introduce BioGlyph, which compiles network topology into an interpretable and transferable language of structural roles. BioGlyph combines graph partitioning and structural measurements to identify roles such as hubs, community cores and cross-community connectors, and fixed rules to translate them into a universal vocabulary. The representation describes each element through its structural role, supporting evidence and semantic consequences, leaving both the network and the LLM unchanged. Across twenty networks spanning five domains, BioGlyph substantially improves open LLMs' ability to answer structural reasoning questions, outperforming edge-based, numerical and learned representations by up to 26 percentage points in system accuracy. Ablations show that the gain comes from explicitly encoding structural roles in semantically interpretable terms. The gain is more prominent in dense, community-structured networks and diminishes in sparse networks whose topology is more readily inferred from text. In a budding-yeast protein-interaction network, BioGlyph exposes biological organization: cross-community connectors are enriched for essential genes, whereas peripheral proteins are depleted. BioGlyph thus provides an interpretable representation for both language models and scientists to reason about network structure.

Typological features are widely used in multilingual NLP, and the prediction of such features holds downstream utility. However, existing methods to predict missing values lack interpretable justifications for predictions, while their performance across resource levels and feature types remains underexplored. Given LLMs' abilities in meta-linguistic reasoning and in providing rationales, we investigate LLMs' performance in typological feature prediction via an in-context learning approach with linguistic data from URIEL+ and Glottolog. We find that zero-shot prompting is insufficient, but when given phylogenetic and geographic neighbour evidence, LLMs substantially outperform all baselines without disadvantaging low-resource languages. We further find that most LLM rationales are consistent with the provided evidence, offering a step toward explainable typological feature prediction.

Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as generations grow longer. A key factor is that they frequently lose track of earlier visual evidence and intermediate constraints under a monolithic growing context. Inspired by how humans separately recall what they see and what they infer when solving complex tasks, we propose DLMR, a parameter-efficient mechanism that equips MLLMs with Dual Latent Memories: a visual memory that compresses image evidence and a reasoning memory that tracks intermediate conclusions and constraints. A Router then dynamically decides which memory and how much to reuse during inference, preserving visual grounding while maintaining coherent long-horizon reasoning. DLMR is trained in three stages, from latent memory construction to selective router learning, while keeping the base MLLM frozen, yielding substantial gains on both general and reasoning benchmarks with only a small number of additional trainable parameters. Analyses further show interpretable, state-dependent routing with specialized memory roles and reduced decoding tokens over long generations. Code is available at https://github.com/Hunter-Wrynn/DLMR.

This study examines the ability of large language models (LLMs) to predict the risk of weather-related forced outages in the distribution grid in a zero-shot framework, without labeled training data. The problem is formulated as a binary severity classification task across three forecast horizons (3h, 6h, 12h), using six years of outage records and high-resolution weather data for a utility service area in central Texas. Four zero-shot LLMs are benchmarked against two supervised classifiers across two input configurations: one using current weather observations and the other using weather forecast data. Results show that supervised models outperform LLMs on macro-F1 and precision, while newer LLM generations achieve competitive scores. Beyond accuracy, LLMs offer complementary strengths in actionable reasoning and geographic scalability, suggesting that combining them with supervised models may be the best practice.

Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: coverage, retaining enough pertinent information to achieve some goal, and conciseness, removing as much irrelevant information as possible. Conformal prediction methods have been used to guarantee coverage, and must be optimized for conciseness through design of a score function. State-of-the-art scoring functions use hand-engineered LLM prompts asking the model to rate the importance of content, but manual prompt engineering is labor-intensive and task-specific. We introduce the Conformal Relevance framework which uses in-context learning example curation and ensembling to create a score function which maintains coverage while improving conciseness with minimal manual input. We demonstrate this framework's application on seven NLP tasks, and also theoretically study the impact of diversity for ensembled conformal scores, giving a complementarity condition that characterizes when ensembling improves worst-case sentence scores, and a saturation bound on ensemble improvement.

Hybrid architectures combining Full Attention (FA) and Linear Attention (LA) are increasingly prominent, yet their allocation remains heuristic. We seek an evidence-grounded basis in head-level functional organization learned by RoPE-based Transformers. Behavioral probes do not yield a complete taxonomy, so we propose two intervention metrics: RoPE Frequency Importance Score (RFIS), measuring how each frequency affects a head's attention distribution, and RoPE Positional Dependence (RPD), isolating dependence on rotary positional modulation. On Qwen3-series models and Llama3.1, RFIS suggests and RPD verifies a complete taxonomy of retrieval and positional heads separated by a salient mid-low-frequency band. Controlled Transformers show that this boundary follows the training-length positional scale; we term it the Global Positional Band (GPBand). The analysis suggests a potential cause of zero-shot length-extrapolation failure and yields two principles: positional modeling should operate only locally, with global access through position-independent retrieval; and both functions should be assigned at head granularity with layer-specific allocation. We instantiate them in Head-wise Hybrid Architecture (HwH), using NoPE FA for global retrieval and LA for local positional modeling. With an FA-to-LA ratio below 1:3, HwH retains strong language modeling and commonsense reasoning while improving retrieval and substantially strengthening zero-shot long-context extrapolation over Transformer, LA, and a layer-wise hybrid baseline. Ablations validate both principles and component roles, highlighting principled hybrid architecture design as a promising route toward future foundation models.

Large Language Models (LLMs) increasingly use user context such as memory, profiles, and role prompts to personalize their responses. This personalization can affect evidence-based judgment: the same evidence may lead to different conclusions under different user contexts. Finance provides a high-stakes setting to study this problem because decisions often depend on interpreting long and complex documents. We test this using 3,575 SEC filings across twelve LLMs. We compare persona-conditioned retrieval, neutral retrieval, and memory-framed context to separate the effect of evidence selection from the effect of interpretation. We find that most user-context spillover comes from how models interpret the same evidence under different roles, rather than from retrieving different evidence. We then test two simple mitigation strategies: expressing the same investor mindset as a user profile instead of an assistant role, and separating evidence-based and personalized outputs. Both reduce spillover, but neither removes it completely, and their effectiveness varies substantially across models.