Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
arXiv:2604.02351v1 Announce Type: new Abstract: Machine learning models deployed in non-stationary environments are exposed to temporal distribution shift, which can erode predictive reliability over time. While common mitigation strategies such as periodic retraining and recalibration aim to preserve performance, they...
Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
arXiv:2604.03141v1 Announce Type: new Abstract: Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-grained factual statements. Existing evaluation methods primarily focus on precision: they decompose a...
Do We Need Frontier Models to Verify Mathematical Proofs?
arXiv:2604.02450v1 Announce Type: new Abstract: Advances in training, post-training, and inference-time methods have enabled frontier reasoning models to win gold medals in math competitions and settle challenging open problems. Gaining trust in the responses of these models requires that natural...
Fast NF4 Dequantization Kernels for Large Language Model Inference
arXiv:2604.02556v1 Announce Type: new Abstract: Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction, inference on current NVIDIA GPUs (e.g.,...
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
arXiv:2604.02869v1 Announce Type: new Abstract: Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation turns. We present the first application of MT-GRPO (Multi-Turn Group Relative Policy Optimization)...
Revealing the Learning Dynamics of Long-Context Continual Pre-training
arXiv:2604.02650v1 Announce Type: new Abstract: Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migrating these small-scale settings to industrial-grade models risks insufficient adaptation...
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
arXiv:2604.02947v1 Announce Type: new Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a...
Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models
arXiv:2604.02772v1 Announce Type: new Abstract: Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce a comprehensive...
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
arXiv:2604.02349v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which...
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
arXiv:2604.02617v1 Announce Type: new Abstract: Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an...
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
arXiv:2604.03173v1 Announce Type: new Abstract: Large language models and deep research agents supply citation URLs to support their claims, yet the reliability of these citations has not been systematically measured. We address six research questions about citation URL validity using...
Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge
arXiv:2604.02621v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an RL...
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
arXiv:2604.02460v1 Announce Type: new Abstract: Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoretical...
Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization
arXiv:2604.02528v1 Announce Type: new Abstract: The new Specifications for the National Bridge Inventory (SNBI), in effect from 2022, emphasize the use of element-level condition states (CS) for risk-based bridge management. Instead of a general component rating, element-level condition data use...
SEDGE: Structural Extrapolated Data Generation
arXiv:2604.02482v1 Announce Type: new Abstract: This paper proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable assumptions on the underlying data generating process. We provide conditions under which data satisfying new specifications can be generated reliably, together...
Querying Structured Data Through Natural Language Using Language Models
arXiv:2604.03057v1 Announce Type: new Abstract: This paper presents an open source methodology for allowing users to query structured non textual datasets through natural language Unlike Retrieval Augmented Generation RAG which struggles with numerical and highly structured information our approach trains...
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
arXiv:2604.02653v1 Announce Type: new Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of...
Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization
arXiv:2604.02666v1 Announce Type: new Abstract: Optimization is as much about modeling the right problem as solving it. Identifying the right objectives, constraints, and trade-offs demands extensive interaction between researchers and stakeholders. Large language models can empower decision-makers with optimization capabilities...
Verbalizing LLMs' assumptions to explain and control sycophancy
arXiv:2604.03058v1 Announce Type: new Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment. We hypothesize that this behavior arises from incorrect assumptions about the user, like...
Generalization Limits of Reinforcement Learning Alignment
arXiv:2604.02652v1 Announce Type: new Abstract: The safety of large language models (LLMs) relies on alignment techniques such as reinforcement learning from human feedback (RLHF). However, recent theoretical analyses suggest that reinforcement learning-based training does not acquire new capabilities but merely...
Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
arXiv:2604.03174v1 Announce Type: new Abstract: Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account of augmentation...
Speaking of Language: Reflections on Metalanguage Research in NLP
arXiv:2604.02645v1 Announce Type: new Abstract: This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs' metalanguage-centered efforts. Finally, we discuss four dimensions...
Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training
arXiv:2604.02637v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across various contexts at scale. Prior mitigation (e.g., AI detectors and disclaimers) largely treats people as...
Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation
arXiv:2604.02557v1 Announce Type: new Abstract: Language models are known to exhibit various forms of cultural bias in decision-making tasks, yet much less is known about their degree of cultural familiarity in open-ended text generation tasks. In this paper, we introduce...
Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
arXiv:2604.02343v1 Announce Type: cross Abstract: We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of more compute. For lossless compression, domain-adapted LoRA adapters can improve...
Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
arXiv:2604.03147v1 Announce Type: new Abstract: We present a method to identify a valence-arousal (VA) subspace within large language model representations. From 211k emotion-labeled texts, we derive emotion steering vectors, then learn VA axes as linear combinations of their top PCA...
An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
arXiv:2604.02596v1 Announce Type: new Abstract: In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can...
Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity
arXiv:2604.02770v1 Announce Type: new Abstract: In large language model (LLM)-driven multi-agent systems, disobey role specification (failure to adhere to the defined responsibilities and constraints of an assigned role, potentially leading to an agent behaving like another) is a major failure...
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
arXiv:2604.03216v1 Announce Type: new Abstract: Large language models (LLMs) often produce confident but incorrect answers in settings where abstention would be safer. Standard evaluation protocols, however, require a response and do not account for how confidence should guide decisions under...
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
arXiv:2604.02525v1 Announce Type: new Abstract: Low-precision training (LPT) commonly employs Hadamard transforms to suppress outliers and mitigate quantization error in large language models (LLMs). However, prior methods apply a fixed transform uniformly, despite substantial variation in outlier structures across tensors....