Large language models

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

26,872 stories · RSS feed

arXiv AI

Jun 16

Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA

arXiv:2604. 06173v2 Announce Type: replace-cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning.

By Kyubyung Chae, Jewon Yeom, Jeongjae Park, Seunghyun Bae, Ijun Jang, Hyunbin Jin, Jinkwan Jang, Taesup Kim

llms benchmarks safety

arXiv AI

Jun 16

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.

By Georgios Syros, Evan Rose, Brian Grinstead, Christoph Kerschbaumer, William Robertson, Cristina Nita-Rotaru, Alina Oprea

llms agents safety

arXiv AI

Jun 16

RollArt: Disaggregated Multi-Task Agentic RL Training at Scale

arXiv:2512. 22560v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU-heavy environment execution, and bursty reward evaluation.

By Wei Gao, Yuheng Zhao, Tianyuan Wu, Shaopan Xiong, Weixun Wang, Dakai An, Lunxi Cao, Dilxat Muhtar, Zichen Liu, Haizhou Zhao, Ju Huang, Siran Yang, Yongbin Li, Wenbo Su, Jiamang Wang, Lin Qu, Bo Zheng, Wei Wang

llms agents reinforcement-learning efficiency

arXiv AI

Jun 16

FasterPy: An LLM-based Code Execution Efficiency Optimization Framework

arXiv:2512. 22827v2 Announce Type: replace-cross Abstract: Code often suffers from performance bugs.

By Yue Wu, Minghao Han, Ruiyin Li, Peng Liang, Amjed Tahir, Zengyang Li, Qiong Feng, Mojtaba Shahin

llms rag fine-tuning benchmarks

arXiv AI

Jun 16

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

arXiv:2606. 15782v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation.

By Pratheswaran Hariharan, Haiping Xu, Donghui Yan

llms rag multimodal safety

arXiv AI

Jun 16

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

arXiv:2510. 16882v4 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks.

By Heming Zou, Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji

llms rag fine-tuning benchmarks safety

arXiv AI

Jun 16

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

arXiv:2603. 10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning.

By Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu

llms benchmarks safety

arXiv AI

Jun 16

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference

arXiv:2510. 07651v3 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size.

By Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao, Enmao Diao

llms efficiency

arXiv AI

Jun 16

Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2

arXiv:2606. 14748v1 Announce Type: cross Abstract: We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes.

By Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez, Aythami Morales, Ruben Tolosana, Ruben Vera-Rodriguez

llms multimodal benchmarks

arXiv AI

Jun 16

RIDGECUT: Learning Graph Partitioning with Rings and Wedges

arXiv:2505. 13986v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has shown promise for combinatorial optimization problems on graphs by learning heuristics that generalize across instances.

By Qize Jiang, Angelo Zangari, Linsey Pang, Alice Gatti, Mahima Aggarwal, Giovanna Vantini, Xiaosong Ma, Weiwei Sun, Sourav Medya, Sanjay Chawla

llms rag reinforcement-learning

arXiv AI

Jun 16

BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios

arXiv:2605. 00873v2 Announce Type: replace-cross Abstract: The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods.

By Advait Tilak, Jiwon Choi, Nazifa Mouli, Wei Le

llms diffusion multimodal benchmarks safety

arXiv AI

Jun 16

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

arXiv:2605. 29796v3 Announce Type: replace Abstract: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search.

By Yunbo Tang, Chengyi Yang, Shiyu Liu, Zhishang Xiang, Zerui Chen, Qinggang Zhang, Jinsong Su

llms agents reinforcement-learning efficiency

arXiv AI

Jun 16

Computational Safety for Generative AI: A Hypothesis Testing Perspective

arXiv:2502. 12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts.

By Pin-Yu Chen

llms diffusion safety

arXiv AI

Jun 16

Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models

arXiv:2606. 16902v1 Announce Type: cross Abstract: This work addresses spatial question answering for service robots traversing long egocentric routes.

By Dongbin Na, Chanwoo Kim, Soonbin Rho, Giyun Choi, Gangbok Lee, Dooyoung Hong

llms rag agents nlp robotics multimodal benchmarks

arXiv AI

Jun 16

Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering

arXiv:2606. 16890v1 Announce Type: cross Abstract: Aggregate accuracy benchmarks conceal a systematic structure in how large language models fail at electronic health record (EHR) question answering: questions requiring more inferential steps produce disproportionately more errors.

By Sanjay Basu

llms nlp benchmarks

arXiv AI

Jun 16

Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment

arXiv:2606. 16799v1 Announce Type: cross Abstract: Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations.

By Zijie Meng

llms efficiency multimodal benchmarks safety

arXiv AI

Jun 16

Unified Multimodal Model for Brain MRI Imputation and Understanding

arXiv:2606. 16484v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold great potential for medicine, as they inherit knowledge from LLM and allow multiple data modalities to be integrated, analysed and interpreted in natural language.

By Zhiyun Song, Che Liu, Tian Xia, Avinash Kori, Wenjia Bai

llms rag multimodal safety

arXiv AI

Jun 16

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.

By Hanyu Lin, Min Cai, Jiawei Wen, Haodi Zhang

llms

arXiv AI

Jun 16

PVminerLLM2: Improving Structured Extraction of Patient Voice via Preference Optimization

arXiv:2606. 16074v1 Announce Type: cross Abstract: Motivation: Patient-generated text contains critical information on patients' lived experiences, social context, and care engagement, but remains largely unstructured, limiting its use in patient-centered outcomes research.

By Samah Fodeh, Linhai Ma, Ganesh Puthiaraju, Srivani Talakokkul, Afshan Khan, Elyas Irankhah, Sreeraj Ramachandran, Ashley Hagaman, Sarah Lowe, Aimee Roundtree

llms fine-tuning benchmarks

arXiv AI

Jun 16

Tool-IQA: Augmenting Image Quality Assessment with Simple Tools

arXiv:2606. 16082v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA).

By Guanyi Qin, Junjie Zhang, Chunming He, Yibing Fu, Jie Liang, Tianhe Wu, Lei Zhang

llms agents multimodal benchmarks

Get the daily briefing