每日文章

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications. We present Grad Detect, a gradient-based approach for predicting hallucinations by analyzing layer-wise gradient patterns from a single forward-backward pass during inference. Our method shows that the internal gradient structure of a model carries rich information about the correctness of its output. This information is not accessible through output-level signals alone. We evaluate Grad Detect on several Q&A benchmarks across both hallucination detection and model abstention prediction, where it consistently outperforms confidence-based and sampling-based baselines. Through comprehensive layer ablation studies across all eleven models from four architectural families, we find that the final five layers concentrate over 97% of the discriminative gradient signal, enabling efficient deployment with minimal performance loss. Grad Detect provides a unified framework for predicting multiple dimensions of LLM reliability, offering strong predictive performance alongside interpretable insights into where and how model failures originate.

While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing." Unintentionally bad contexts can happen without malicious jailbreaking intents: For example, a user asks the model to justify an incorrect math theorem or fails to correct the model's buggy code. Specifically, we investigate ``pigeonholing" in two scenarios: (1) when the user suggests a solution, and (2) when the conversation context includes the assistant's previous (incorrect) responses. Our experiments across 10 verifiable and open-ended tasks with 10 different models show that pigeonholing manifests in several ways: (1) repeating the incorrect answers from context (leading to 38-40% performance drop), (2) converging on a narrow set of answers in coding and text generation without exploring alternatives, and (3) flipping stance on controversial topics to align with the user or the assistant's previous claims. We find that pigeonholing worsens almost monotonically with the number of conversation turns (performance drops by additional 14+% as repeated mistakes increase from 1 to 5), and pigeonholing-induced mode collapse can happen even when the provided example is correct. As a step toward mitigation, we propose RLVR with synthetic errors which improves models by 43-60% under bad contexts compared to vanilla RLVR baselines.

Data augmentation is a simple and model-agnostic approach for exploiting known invariances in learning problems. Given a group acting on the input space, one augments the training set with transformed copies of each sample. Because it exploits symmetries without modifying the underlying learning algorithm, data augmentation can be applied broadly across learning methods. However, this universality comes at a computational cost: when the group is large, full group-sized augmentation quickly becomes computationally infeasible. This raises a fundamental question: Can partial data augmentation achieve the same statistical benefits as full augmentation in terms of generalization and sample complexity? We develop a general framework for investigating this question using Fourier analysis and the representation theory of finite groups. We show that, for a broad class of classical learning problems, partial data augmentation based on a randomly sampled subset of group elements achieves the same minimax rates as full augmentation, up to an approximation error that vanishes as the subset size increases. Our results provide a theoretical explanation for why partial augmentation can retain the statistical benefits of full augmentation despite enforcing symmetry only approximately, and shed light on a recently raised question in learning with symmetries: whether statistically optimal learning under general group invariances can be achieved using computationally scalable methods. Moreover, we prove a complementary impossibility result: enforcing exact invariance via data augmentation requires averaging over the entire group, and cannot be achieved by any strict subset when the hypothesis space is sufficiently expressive. Together, these results provide a unified perspective on full and partial data augmentation, as well as exact and approximate symmetry enforcement.

Motivated by an application in machine learning optimization, this paper focuses on the challenges of sampling a matrix uniformly from the unit spectral norm ball. It is proven that all singular values of sampled matrices converge to 1 almost surely as the matrix dimensions increase. This result provides the theoretical justification for a proposed simple sampling method applicable for large dimension sizes matching matrices found in modern large language models. Experimental results demonstrate both the convergence of the singular values, as well as the exact and proposed approximate sampling methods.

Large Language Models (LLMs) and LLM-based Multi-Agent Systems (MAS) are revolutionizing software engineering (SE) by advancing automation, decision-making, and knowledge processing. Their recent application to SE tasks has already shown promising results. In this paper, we focus on summarization as a key application area. We present Metagente, an LLM-based MAS designed to generate concise and accurate summaries of software documentation. Metagente employs a Teacher-Student architecture where multiple LLM agents collaborate to enhance relevance and precision of produced summaries. An empirical evaluation on real-world datasets demonstrates Metagente's effectiveness in streamlining workflows, outperforming the considered baselines. The evaluation provides evidence that Metagente improves summarization for requirements analysis and technical documentation. Our findings underscore the transformative potential of these technologies in SE, while identifying challenges and future research directions for their seamless integration.

Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs. These methods ignore the different functionalities of attention heads, leading to the eviction of critical tokens and thus degrading the performance of LLMs. To address this issue, we propose CompressKV, a resource-efficient KV-cache compression framework for GQA-based LLMs. Instead of aggregating attention scores from all heads, CompressKV identifies Semantic Retrieval Heads (SRHs) that capture both the initial and final tokens of a prompt and semantically important mid-context evidence, and uses them to select tokens whose KV pairs should be retained. Furthermore, CompressKV allocates cache budgets across layers according to offline estimates of layer-wise eviction error. Experiments on LongBench and Needle-in-a-Haystack show that CompressKV consistently outperforms existing KV-cache eviction methods across memory budgets. Notably, it preserves over 97\% of full-cache performance using only 3\% of the KV cache on LongBench question-answering tasks and achieves 90\% accuracy with just 0.7\% KV storage on Needle-in-a-Haystack. These results demonstrate an improved resource--performance trade-off for long-context LLM inference. Our code is publicly available at: https://github.com/TUDa-HWAI/CompressKV

Accurate user modeling often depends on rich interaction histories, which are unavailable for billions of low-activity users. Large Language Models (LLMs) can infer latent user states from static profiles, but this reasoning becomes unreliable when profiles are sparse, and applying an LLM to billions of users is prohibitively expensive. We present ScaleToT, which learns structured reasoning from a small LLM-processed subset and extends it to the broader low-activity user population. To improve reasoning reliability, ScaleToT constructs typed user-state chains with a bounded entropy-guided Tree-of-Thought (ToT) refinement procedure. To make this structured reasoning usable from sparse profiles, the teacher-curated chains are used to train a student model on static profiles through supervised fine-tuning (SFT) and Outcome-Driven Segment-Aware Implicit Reward Policy Optimization (OSIPO). ScaleToT then transfers the student's reasoning representations to a lightweight profile encoder, providing shared reasoning signals for the remaining users without LLM inference. We evaluate ScaleToT on lifetime value (LTV) prediction in a billion-scale advertising deployment. A randomized online A/B test increased LT30 by 6.738\%, while offline reasoning covered only 7.32\% of the potential population, greatly reducing compute cost compared with full-population reasoning.

Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual attention scores. However, we show that attention is often dominated by a model-induced prior: even without textual instruction, MLLMs tend to focus on certain task-agnostic regions. Consequently, the attention scores of instruction-conditioned tokens are suppressed, increasing the risk that these tokens are discarded during pruning. To address this issue, we propose Prior-Corrected Token Reduction (PriorTR), a training-free token reduction method that explicitly separates task-conditioned attention from the model-induced prior. PriorTR estimates the attention map of the prior, and contrasts it with the task-conditioned attention distribution to measure the additional usable information contributed by each visual token. Importantly, PriorTR computes both the model-induced prior and the task-conditioned posterior within a single forward pass by introducing a null token that serves as an instruction-agnostic probe in the attention block. This design avoids duplicated propagation. Extensive experiments across multiple multimodal benchmarks and MLLMs demonstrate that PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines, particularly under aggressive token budgets.

Long video understanding remains a daunting challenge for \emph{Multimodal Large Language Models} (MLLMs) due to the excessive computation and memory footprint. Thus, \emph{keyframe selection} is often adopted to mitigate this shortcoming, which however still suffers from low flexibility and high noise due to its hard sampling principle. In this paper, we define video frame selection as a problem of \emph{Quasi-Gaussian Sampling}, and propose an adaptive and training-free approach termed \textbf{\emph{AdaQ}}. Inspired by the \(3\)-\(σ\) rule of Gaussian distribution, the objective of AdaQ is to achieve the optimal \(3\)-\(σ\) interval for different examples, \emph{i.e.}, a smaller \(3\)-\(σ\) interval for the local query and a larger one for the global query, thereby facilitating robust and adaptive frame sampling. To validate AdaQ, we apply it to four MLLMs with three embedding models. The extensive experimental results not only show its obvious performance gains over the default MLLMs and the SOTA keyframe selection methods, \emph{e.g.}, helping Qwen3-VL-8B outperform GPT4o by 15.8\% on average by using only 64 frames, but also confirm its superior robustness and high efficiency for long-video understanding, \emph{e.g.}, \textbf{only 1 hyper-parameter} needs to be set. \textbf{Our code project} is given at \href{https://github.com/Zkayovo-xmu/AdaQ}{https://github.com/Zkayovo-xmu/AdaQ}.

Contextual entrainment, which is a newly discovered phenomenon in large language models (LLMs), refers to the tendency of a model to assign higher probabilities to tokens that appear in its context. In this work, we extend this phenomenon from the token level to the sentence level by examining the per-token mean log-probability of a sentence instead of the probabilities of individual tokens. We investigate sentence-level contextual entrainment across 26 LLMs from seven families and two datasets, which cover both subjective and objective tasks. We find that sentence-level contextual entrainment exists. This means that the sentences in the prompt (even if they are counterfactual statements) can significantly increase their probability during model inference time. As the model size increases, contextual entrainment gradually decreases. We also find that contextual entrainment is controlled by 2% to 4% of the attention heads. Turning off these attention heads can effectively mitigate contextual entrainment without hurting the model's performance.

Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model responses and, for each problem, constructs both autonomous and strategy-guided trajectories to enable direct comparison of the model's behavior with and without strategic guidance. The framework then addresses two key questions. For how to distill, a token-level forward-KL objective selectively transfers the distributional shift induced by strategy conditioning into the unguided policy, with proximal constraints ensuring stability. For when to distill, adaptive instance-level weighting strengthens guidance when autonomous exploration falls short and reduces it as the model's own competence grows. Experiments on four mathematical benchmarks across two model families show that SGPO consistently outperforms SFT, on-policy RL, and hybrid-policy baselines, improving the average score by 2.2 points over the strongest baseline on Qwen2.5-7B-Instruct. Analysis reveals that the forward-KL objective provides an inherently selective distillation signal that outperforms direct trajectory imitation, and that strategy distillation exhibits complementary scaling with base model capability.

Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external tools and environments. However, their autonomy poses significant safety risks: agents may execute destructive commands, leak sensitive data, or violate domain constraints. Existing safety approaches face a fundamental tradeoff: hand-crafted rules are interpretable but brittle, with overly conservative rules blocking safe operations (high false positives) while permissive rules miss unsafe behaviors (high false negatives). Neural classifiers lack the interpretability required for safety-critical deployments. We present AutoSpec, a framework that automatically evolves deployed expert-designed safety rules from user safe/unsafe annotations through counterexample-guided inductive synthesis (CEGIS) guided by inductive logic programming (ILP). Starting from the expert rules and a stream of annotated traces, AutoSpec iteratively evaluates rules, mines false-positive and false-negative counterexamples, uses ILP to learn which predicates discriminate them, generates candidate rule edits, and verifies candidates to select the best revision. The key insight is that ILP efficiently identifies predicates that appear frequently in false negatives but rarely in false positives (or vice versa), dramatically pruning the exponential search space of rule edits. This continues until convergence, producing interpretable rules that balance precision and recall. We evaluate AutoSpec on 291 execution traces spanning code execution and embodied agent domains. AutoSpec raises rule F1 to 0.98 and 0.93 across the two domains, achieving up to 94% false positive reduction while maintaining high recall, and converges within 4-5 iterations. The ILP-guided approach achieves up to 4.8x higher F1 than heuristic CEGIS. The learned rules are human-readable, auditable, and generalize to unseen scenarios.

As large language models (LLMs) are increasingly used in media production from journalistm to filmmaking, what impact do they have on the stories being told? Prior work has shown LLMs to perpetuate social biases, including those related to gender. We complement existing literature on gender bias in LLM outputs by auditing the network structure of LLM-generated movie screenplays through automating the Bechdel test, a popular measure of women's representation in literary and film works. We also introduce the use of social network analysis measures to further analyze representational bias in LLM-generated scripts. We evaluate screenplays generated by three state-of-the-art LLMs (GPT-5, Gemini 3 Pro, and Claude Sonnet 4.5) against 768 corresponding human-written screenplays, finding that human-written scripts are more likely to pass the Bechdel test. However, other network analyses, like centrality, homophily, and triadic relationships demonstrate that in some cases LLM-scripts have less bias, although all script types demonstrate some representational bias under most measures. We conclude by discussing the continued need for further quantitative assessments of media representations and AI-generated content.

Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performance. Existing token pruning methods typically rely on single-layer signals, such as attention scores or token similarities, which overlook the cross-layer transformation of visual representations and may exhibit positional bias in multimodal token sequences. To address this limitation, we propose a training-free token pruning framework based on Cross-Layer Spectral Evolution (CLSE). Instead of measuring token importance from single-layer feature magnitudes, CLSE quantifies how token representations evolve across Transformer layers in the frequency domain. This evolution reflects the transition from high-frequency structural details to low-frequency semantic abstractions. We observe that tokens with stronger spectral redistribution across layers are more likely to be semantically active and should therefore be preserved. By modeling cross-layer token dynamics, CLSE provides a stable importance criterion that mitigates positional bias. Extensive experiments on both image and video benchmarks demonstrate that CLSE achieves a superior trade-off between efficiency and accuracy under aggressive token reduction. Across multiple MLLMs, CLSE reduces FLOPs, KV cache memory, and latency while maintaining competitive or improved performance.

We discuss reasons why the scaling exponents of current Large Language Models (LLMs) applications are indicating an unsustainable regime in terms of energy resources. We further show that attributing the smallness of such exponents to a numerical bias due to the neglect of a non-zero value of the loss function in the limit of infinite data (``pedestal effect") does not remove the unsustainability issue. Finally, the effects of the smoothness (roughness) of the data on the scaling exponents is commented upon based on an analogy with phenomenological models of fluid turbulence.

Quantum computers could outperform classical machines on important problems, but only if the errors that pervade quantum hardware can be corrected at scale. Quantum low-density parity-check (qLDPC) codes offer a promising route to this goal by combining sparse parity checks with finite encoding rate and growing distance, but their construction remains a challenging discrete design problem. Here we introduce structured concept evolution (SCE), a search framework that pairs a large language model with a structured algebraic mutation grammar to discover lifted-product code families, a class of CSS qLDPC codes. Instead of asking the LLM to design codes from first principles, SCE evolves structured concepts consisting of algebraic specifications paired with executable programs that realize them, using hierarchical mutations that modify the group algebra, protograph geometry, or base space. Running SCE, we discover a diverse set of competitive code families, ranging from abelian constructions to families over non-abelian groups beyond those underlying standard designs such as bivariate-bicycle codes, and characterize them under code-capacity depolarizing noise with BP+OSD decoding. These results are obtained with lightweight models (GPT-5.4-mini and GPT-5.4-nano).

The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevant to large language models (LLMs), which produce narratives across a wide range of languages and cultural contexts. However, it remains uncertain whether these models preserve culturally grounded meaning when equivalent moral lessons are conveyed through distinct cultural forms. This study introduces a multilingual evaluation narrative framework that integrates a cross-linguistic collection of 414 proverbs spanning 15 languages and uses four LLMs to generate 13k narratives. By employing semantically equivalent proverbs as culturally grounded prompts, the analysis assesses whether models preserve meaning across languages, how cross-lingual conditioning influences narrative realization, and whether different model families converge on similar interpretations. Results indicate that cross-lingual prompting largely preserves proverb-level semantic meaning while systematically redistributing agency, social positioning, and narrative structure. Additionally, strong inter-model convergence is observed in both monolingual and cross-lingual settings, suggesting that multilingual LLMs rely on shared semantic abstractions despite architectural and linguistic differences. These findings shed light on the need for more comprehensive evaluations of cultural grounding. Relying exclusively on semantic similarity in multilingual narrative assessments may overestimate cultural preservation by neglecting culturally meaningful variations in narrative expression.

The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creating artificial neural networks capable of continual learning. Although this phenomenon has been known for decades, it has mostly been studied in older, relatively small architectures and rarely in natural-language domains. To determine whether loss of plasticity remains a problem in the modern transformer-based LLM paradigm, we study plasticity loss in GPT-style Transformer models trained on a multilingual continual learning problem. Consistent with prior work, we find evidence of plasticity loss across models ranging from 5M to 314M non-embedding parameters, as measured by deterioration on a held-out Vietnamese probing task. We further find that the onset of plasticity loss follows a predictable scaling law, growing sublinearly with model size. These results suggest that larger models may delay the measurable effects of plasticity loss, but that increasing parameter count alone is likely to be insufficient to completely prevent it. We also find evidence of plasticity loss under stationary multilingual training, challenging the view that the phenomenon is exclusive to continual learning with abrupt task changes. Overall, our results suggest that even large Transformer language models trained on natural-language will eventually lose the ability to efficiently adapt to new data after sufficiently long training, in both continual and stationary settings.

We develop a comprehensive theory for regularized M-estimation in reproducing kernel Hilbert spaces. Under mild conditions on the loss we establish existence and measurability of the estimator, covering a wide range of convex and non-convex losses, including bounded robust losses. We further prove sharp rates of convergence with an explicit bias-variance decomposition governed by a novel complexity measure. We show that the variance is independent of misspecification, while the bias depends on a source condition parameter known in the learning literature. For tensor product Sobolev spaces we obtain new rates that connect to spaces of functions with dominating mixed smoothness, substantially extending existing results and explaining why these estimators circumvent the curse of dimensionality. Our methodology, combining elements from both functional analysis and empirical process theory, allows for an asymptotic linearisation of the objective function that avoids both closed-form solutions and global Lipschitz assumptions, and may be of independent interest. The estimators are implemented in C++ and theory is supported by numerical experiments.

On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck. Existing systems primarily optimize for decoding speed, implicitly assuming that faster execution is always preferable. We show instead that on-device LLM inference often has exploitable configuration slack: modestly lowering NPU and memory frequencies preserves quality of experience (QoE) while substantially improving energy efficiency and reducing heat. Realizing this opportunity in production is challenging. The most energy-efficient NPU/DDR setting varies with the model, inference engine, platform, and runtime conditions, with no stable ranking across configurations. Commercial devices further lack component-level power sensing, and shell temperature evolves with request arrivals, response lengths, and thermal history. To address these challenges, we propose EnerInfer, the first on-device LLM inference framework that jointly manages energy efficiency, throughput, and thermal comfort for LLM workloads. EnerInfer replaces per-model profiling and sensor-heavy control with disaggregated, model-structure-aware prediction and ranking-driven online feedback. It predicts throughput and power for unseen LLMs across NPU/DDR frequency settings, selects QoE-satisfying efficient configurations under runtime interference, and uses lightweight limited-horizon thermal prediction to dynamically switch between energy-optimized and thermally constrained inference. Evaluations on real-world LLMs show that EnerInfer improves energy efficiency by up to 65%, 12%, and 24% on phones, a laptop, and a development board, respectively, without QoE violation.