Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

18,449 stories · RSS feed

arXiv Machine Learning

Aug 5

TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series

arXiv:2608. 03391v1 Announce Type: new Abstract: Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, financial services, and logistics, where brief evidence may hide inside long spans of high-frequency data.

By Nicolas Zumarraga, Lorenzo Steno, Ning Wang, Max Rosenblattl, Thomas Kaar, Maxwell A. Xu, Kevin O'Sullivan, Markus Kreft, Elgar Fleisch, Paul Schmiedmayer, Patrick Langer, Robert Jakob

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 5

Robust General Utility for Reinforcement Learning

arXiv:2608. 03562v1 Announce Type: new Abstract: Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications.

By Zixuan Liu, Fangzheng Wu, Brian Summa, Zizhan Zheng

llms reinforcement-learning safety

arXiv Machine Learning

Aug 5

CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning

arXiv:2608. 03673v1 Announce Type: new Abstract: Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning.

By Jian Zhang, Bingyi Wang, Yizhi Liu

llms reinforcement-learning efficiency safety

arXiv Machine Learning

Aug 5

Sparse Weight Decomposition for Efficient Circuit Extraction

arXiv:2608. 03913v1 Announce Type: new Abstract: Dense pretrained transformers do not naturally expose interpretable units for circuit extraction.

By Chuanhao Yan, Xuhan Huang, Yawen Duan, Zhenfei Yin, Hang Zhao, Bryan Dai, Jie Fu

llms fine-tuning benchmarks safety

arXiv Machine Learning

Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun

llms diffusion reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Aug 5

DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

arXiv:2608. 03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly.

By Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang

llms agents benchmarks safety

arXiv Machine Learning

Aug 5

LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation

arXiv:2608. 03382v1 Announce Type: cross Abstract: Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendation.

By Eugene Lee, Oseong Choi, Byungsoo Kang, Taeyeong Jang

llms reinforcement-learning safety

arXiv Machine Learning

Aug 5

The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works

arXiv:2607. 21273v2 Announce Type: replace Abstract: Dense per-step supervision is the standard remedy for sparse-reward long-horizon LLM agents: reward the policy for predicting its next observation, which looks provably safe under potential-based shaping.

By Yu Wang

llms agents

arXiv Machine Learning

Aug 5

SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA

arXiv:2509. 25459v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors.

By Haozhou Xu, Dongxia Wu, Matteo Chinazzi, Ruijia Niu, Rose Yu, Yi-An Ma

llms rag nlp benchmarks

arXiv AI

Aug 5

Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling

arXiv:2608. 02618v1 Announce Type: new Abstract: Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions.

By Tairan Fu, Javier Conde, Carlos Arriaga, Gonzalo Mart\'inez, Pedro Reviriego, Javier Coronado-Bl\'azquez

llms benchmarks

arXiv AI

Aug 5

Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection

arXiv:2608. 03627v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexplored.

By Razieh Chalehchaleh, Reza Farahbakhsh, Noel Crespi

llms benchmarks safety

arXiv AI

Aug 5

A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation

arXiv:2608. 03620v1 Announce Type: cross Abstract: Activation patching and weight-space ablation both claim a component is causally responsible for a behavior, yet they act on different objects: one forward pass versus the parameters behind every forward pass.

By Abdallah Khemais

llms benchmarks

arXiv AI

Aug 5

Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement

arXiv:2608. 03733v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate.

By Chunyang Jiang, Pingping Zhang, Yuzhi Zhao, Wenao Ma, Zhijian Hou, Mengyang Wu, Yiyang Cai, Senkang Hu, Sitong Cheng, Chi-Min Chan, Wei Xue, Yike Guo

llms nlp multimodal benchmarks

arXiv AI

Aug 5

Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks

arXiv:2608. 03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved.

By Mohsen Arjmandi

llms rag benchmarks

arXiv AI

Aug 5

Large language models for partial differential equation workflows

arXiv:2608. 03600v1 Announce Type: new Abstract: Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governing equations, numerical solvers, diagnostics, and decisions.

By Han Wan, Rui Zhang, Hao Sun

llms benchmarks

arXiv AI

Aug 5

Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training

arXiv:2608. 03660v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models.

By Yibei Liu, Jiajun Chen, Qianle Zhang, Tangyue Jin, Mengying Zhu, Meng Xi, Yangyang Wu

llms fine-tuning multimodal benchmarks

arXiv AI

Aug 5

LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards

arXiv:2608. 03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy.

By Zhinan Liu, Jie Li, Mingyu Kang, Jiayi Ji

llms safety

arXiv AI

Aug 5

When Policies Change Probabilities: Modular Decision-Making for LLM Code Review

arXiv:2608. 02677v1 Announce Type: cross Abstract: LLM code reviewers often estimate patch risk and make approval decisions in one prompt.

By Rasvik Kudum, Max Corbett, Hitansh Paliwal, Romaisa Fatima, Thomas Jiralerspong, Sneheel Sarangi

llms

arXiv AI

Aug 5

SAGE: Semantic Explainability of Attention-Based Survival Models in Computational Pathology

arXiv:2608. 02803v1 Announce Type: cross Abstract: Attention-based multiple instance learning (ABMIL) is the predominant approach for slide-level prediction in computational pathology, yet its attention maps provide only local explanations: they indicate where a model focuses but not which histological features drive its predictions or how the model behaves across a patient cohort.

By Abdallah Lamane, Abdul Rahman Diab, Ren-Chin Wu, William Lotter

llms multimodal benchmarks

arXiv AI

Aug 5

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling

arXiv:2608. 02951v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model.

By Evan Assmus, Qining Zhang, Lei Ying

llms reinforcement-learning robotics fine-tuning

Get the daily briefing