Large language models

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

28,264 stories · RSS feed

arXiv AI

Jun 18

Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep

arXiv:2606. 18596v1 Announce Type: cross Abstract: Sleep diaries are central to behavioral sleep medicine and cognitive behavioral therapy for insomnia, yet daily completion is difficult to sustain, and static forms often provide limited context for interpreting night-to-night sleep variation.

By Amama Mahmood, Bokyung Kim, Honghao Zhao, Molly E. Atwood, Luis F. Buenaver, Michael T. Smith, Chien-Ming Huang

llms

arXiv Machine Learning

Jun 18

Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.

By Yanjun Shao, Yundi Chen, Yashvi Patel, Aurelien Pelissier, Mar\'ia Rodr\'iguez Mart\'inez

llms rag nlp multimodal benchmarks safety

arXiv Machine Learning

Jun 18

Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation

arXiv:2606. 19315v1 Announce Type: new Abstract: Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years.

By Ruida Wang, Rui Pan, Pengcheng Wang, Shizhe Diao, Tong Zhang

llms diffusion benchmarks

arXiv AI

Jun 18

TW-LegalBench: Measuring Taiwanese Legal Understanding

arXiv:2606. 18699v1 Announce Type: cross Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal reasoning remains underexplored.

By Fei-Yueh Chen, Chun Huang Lin, Chan Wei Hsu, Kuan Hsuan Yeh, Zih-Ching Chen, Kuan-Ming Chen, Patrick Chung-Chia Huang

llms benchmarks

arXiv Machine Learning

Jun 18

REVES: REvision and VErification--Augmented Training for Test-Time Scaling

arXiv:2606. 18910v1 Announce Type: new Abstract: Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning.

By Yuanxin Liu, Ruida Zhou, Xinyan Zhao, Amr Sharaf, Hongzhou Lin, Arijit Biswas, Mohammad Ghavamzadeh, Zhaoran Wang, Mingyi Hong

llms reinforcement-learning benchmarks

arXiv AI

Jun 18

Rescaling MLM-Head for Neural Sparse Retrieval

arXiv:2606. 18811v1 Announce Type: cross Abstract: Learned sparse retrieval (LSR) models such as SPLADE have traditionally used BERT-style masked language models as backbone encoders.

By Youngjoon Jang, Seongtae Hong, Jonah Turner, Heuiseok Lim

llms benchmarks

arXiv AI

Jun 18

Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

arXiv:2606. 18837v1 Announce Type: cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks.

By Hehai Lin, Qi Yang, Chengwei Qin

llms agents benchmarks

arXiv Machine Learning

Jun 18

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

arXiv:2606. 18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local.

By William Kalikman, Ivo Petrov, Dimitar I. Dimitrov, Martin Vechev

llms rag efficiency safety

arXiv AI

Jun 18

ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

arXiv:2606. 19079v1 Announce Type: new Abstract: The increasing deployment of parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters.

By Enrico Cassano, Micha{\l} Brzozowski, Zuzanna Dubanowska, Paolo Mandica, Neo Christopher Chung

llms rag diffusion nlp fine-tuning

arXiv Machine Learning

Jun 18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv Machine Learning

Jun 18

Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health

arXiv:2606. 18506v1 Announce Type: new Abstract: Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue.

By Saba A. Farahani, Elahe Khatibi, Manoj Vishwanath, Amir M. Rahmani, Hung Cao

llms multimodal safety

arXiv AI

Jun 18

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization

arXiv:2508. 09191v2 Announce Type: replace-cross Abstract: Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance.

By Xiaoyu Tao, Shilong Zhang, Mingyue Cheng, Daoyu Wang, Tingyue Pan, Bokai Pan, Changqing Zhang, Shijin Wang

llms nlp fine-tuning safety

arXiv AI

Jun 18

SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

arXiv:2601. 12805v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks.

By Xiaohan Huang, Meng Xiao, Chuan Qin, Qingqing Long, Jinmiao Chen, Yuanchun Zhou, Hengshu Zhu

llms benchmarks safety

arXiv AI

Jun 18

Improve Large Language Model Systems with User Logs

arXiv:2602. 06470v3 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constrained by the scarcity of high-quality data and diminishing returns from rising computational costs.

By Changyue Wang, Weihang Su, Qingyao Ai, Xingzhao Yue, Rui Zhang, Xiaojia Chang, Yiqun Liu

llms rag benchmarks

arXiv AI

Jun 18

PatchWorld: Gradient-Free Optimization of Executable World Models

arXiv:2605. 30880v2 Announce Type: replace-cross Abstract: Text-agent environments are typically modeled as partially observable Markov decision processes (POMDPs), assuming that the simulator's latent state and transition dynamics are hidden from the agent.

By Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong, Tianshi Zheng, Yixia Li, Tianqing Fang, Yufei Li, Yisen Gao, Haoyu Huang, Zhongwei Xie, Hong Ting Tsang, Zihao Wang, Lihui Liu, Jeff Z. Pan, Yangqiu Song

llms agents reinforcement-learning safety

arXiv AI

Jun 18

Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation

arXiv:2606. 18315v1 Announce Type: cross Abstract: Sequential output generation with large-scale Transformer and diffusion decoders pays a memory cost that grows with sequence length, plus iterative per-step computation.

By Tianyu Wang, Ying Wang, Zhihao Liu, Xi Vincent Wang, Lihui Wang

llms diffusion robotics benchmarks

arXiv AI

Jun 18

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents

arXiv:2603. 00026v2 Announce Type: replace-cross Abstract: Memory management is essential for LLM agents in long-term interactions.

By Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yaqin Jin, Yazhong Zhang, Wei Hu

llms agents benchmarks

arXiv AI

Jun 18

Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models

arXiv:2606. 18324v1 Announce Type: cross Abstract: SWave is a complex-valued recurrent language model (169.

By Ramprasath Ganesaraja, Swathika N, Sahil Dilip Panse

llms rag

arXiv AI

Jun 18

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

arXiv:2606. 18310v1 Announce Type: cross Abstract: Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications.

By Xinru Liu, Xianglong Zhang, Di Cai, Zhumin Chen, Pengfei Hu, Xin Xin

llms rag robotics benchmarks

arXiv AI

Jun 18

From Paper to Program: Externalizing and Diagnosing Knowledge Bottlenecks in AI-Assisted Quantum Many-Body Code Generation

arXiv:2604. 04089v4 Announce Type: replace-cross Abstract: Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions rather than explicit equations.

By Yi Zhou

llms benchmarks

Get the daily briefing