Large language models

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

26,473 stories · RSS feed

arXiv AI

Jun 29

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

arXiv:2604. 00757v2 Announce Type: replace-cross Abstract: Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens.

By Dong-Jae Lee, Sunghyun Baek, Junmo Kim

llms efficiency

arXiv AI

Jun 29

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

arXiv:2606. 27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives.

By Avni Mittal

llms agents

arXiv AI

Jun 29

AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization

arXiv:2605. 08704v2 Announce Type: replace Abstract: Multi-agent reasoning has shown promise for improving the problem-solving ability of large language models by allowing multiple agents to explore diverse reasoning paths.

By Hyunmin Hwang, Jaemin Kim, Choonghan Kim, Hangeol Chang, Jong Chul Ye

llms agents benchmarks

arXiv AI

Jun 29

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

arXiv:2606. 27881v1 Announce Type: cross Abstract: Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience across time.

By Emanuela Boros

llms nlp

arXiv AI

Jun 29

Single and Multi Truth Data Fusion using Large Language Models

arXiv:2606. 28062v1 Announce Type: cross Abstract: Data fusion, also known as truth discovery, is a data integration problem that aims to determine the correct value or set of values for each attribute of an object when presented with potentially conflicting values from multiple sources.

By Hira Beril Kucuk, Norman W Paton, Jiaoyan Chen, Zhenyu Wu

llms benchmarks

arXiv Machine Learning

Jun 29

Test-Input Generation for Tensor Programs: What Actually Finds Kernel Bugs

arXiv:2606. 27396v1 Announce Type: cross Abstract: Test-input generation for tensor kernels is folkloric.

By Dipankar Sarkar

llms safety

arXiv AI

Jun 29

Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation

arXiv:2606. 27732v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) recover masked tokens in parallel, offering significant speedups over autoregressive (AR) generation.

By Yuhang Chen, Xianfeng Wu, Jinhao Duan, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Tianlong Chen

llms diffusion efficiency benchmarks

arXiv AI

Jun 29

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

arXiv:2606. 28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood.

By Yanchen Yin, Dongqi Han, Linghui Li

llms benchmarks safety

arXiv AI

Jun 29

PRISON: Unmasking the Criminal Potential of Large Language Models

arXiv:2506. 16150v4 Announce Type: replace-cross Abstract: As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify.

By Xinyi Wu, Geng Hong, Pei Chen, Yueyue Chen, Xudong Pan, Min Yang

llms robotics benchmarks safety

arXiv AI

Jun 29

What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG Agent

arXiv:2606. 26519v2 Announce Type: replace Abstract: Large language models (LLMs) can make scientific software easier to use.

By Zhiyuan Xu, Yueqing Dai, Junling Li, Junwen Luo

llms agents benchmarks safety

arXiv AI

Jun 29

SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion

arXiv:2606. 27876v1 Announce Type: cross Abstract: Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation.

By Haoyu Zhang, Meng Liu, Qianlong Xiang, Kun Wang, Yaowei Wang, Liqiang Nie

llms multimodal benchmarks

arXiv AI

Jun 29

Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs

arXiv:2606. 28122v1 Announce Type: cross Abstract: Neural operators provide deep neural networks for learning mappings between function spaces.

By Alex Colagrande, Paul Caillon, Eva Feillet, Alexandre Allauzen

llms benchmarks safety

arXiv Machine Learning

Jun 29

Realistic honeypot evaluations for scheming propensity

arXiv:2605. 29729v2 Announce Type: replace Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity.

By Victoria Krakovna, David Lindner, Lewis Ho, Sebastian Farquhar, Rohin Shah

llms safety

arXiv AI

Jun 29

STAG: Spatio-temporal Evolving Structural Representation of Action Units for Micro-expression Recognition

arXiv:2606. 28083v1 Announce Type: cross Abstract: Micro-expression recognition is challenging due to subtle and short-lived facial muscle movements.

By Nandani Sharma, Varun Sharma, Dinesh Singh

llms computer-vision safety

arXiv AI

Jun 29

Dialogue to Detection: A Multimodal Hybrid NLP Pipeline for Insurance Fraud Detection

arXiv:2606. 28002v1 Announce Type: cross Abstract: Insurance fraud imposes substantial financial losses and operational inefficiencies, raising premiums and impacting trust among legitimate policyholders.

By Muhammad Shakeel Akram, Amal Htait, Abdul Hamid Sadka, Emma Meisingseth, Karishma Jaitly

llms rag agents nlp multimodal

arXiv AI

Jun 29

Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy

arXiv:2606. 27936v1 Announce Type: cross Abstract: The widespread collection of fine-grained location data by commercial data brokers creates a re-identification risk that is not widely recognised by the public.

By Oscar Thees, Roman M\"uller, Matthias Templ

llms agents safety

arXiv Machine Learning

Jun 29

On the Effect of Uncertainty on Layer-wise Inference Dynamics

arXiv:2507. 06722v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations.

By Sunwoo Kim, Haneul Yoo, Alice Oh

llms safety

arXiv Machine Learning

Jun 29

The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment

arXiv:2606. 27739v1 Announce Type: new Abstract: Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive stepwise annotations.

By Tianyu Jia, Yue Fang, Hongxin Ding, Rihong Qiu, Zhibang Yang, Zhijing Wu, Xu Chu, Junfeng Zhao, Yasha Wang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 29

Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis

arXiv:2606. 27634v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly being considered for deployment on edge devices such as laptops, enabling private, low-latency, and locally personalized applications.

By Thomas S. Paula, Lucas S. Kupssinsk\"u, Rodrigo C. Barros

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 29

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

arXiv:2510. 18874v3 Announce Type: replace Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting.

By Howard Chen, Noam Razin, Karthik Narasimhan, Danqi Chen

llms reinforcement-learning fine-tuning

Get the daily briefing