Large language models

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

23,195 stories · RSS feed

arXiv AI

Jul 10

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

arXiv:2604. 11530v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information.

By Yvon Apedo, Martyna Poreba, Michal Szczepanski, Samia Bouchafa

llms efficiency multimodal safety

arXiv AI

Jul 10

PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs

arXiv:2607. 08269v1 Announce Type: new Abstract: Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML.

By Ying Liu, Yi Ye, Quanyu Feng, Mingxi Ye, Mingtao Zhang, Haoyang Li, Chen Jason Zhang, Qing Li

llms rag benchmarks

arXiv AI

Jul 10

Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

arXiv:2607. 08602v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality.

By Peng Cui, Jitao Wang, Siyan Xue, Yao Huang, Haoming Xia, Dong Li, Dengxiang Liu, Weilin Wang, Liping Liu, Leida Zhang, Yunfu Cui, Tao Peng, Daolin Ji, Haitao Zhao, Wei Zhang, Xiaojuan Wang, Weijie Ma, Zongren Ding, Jinlong Li, Yuan Ding, Jiajing Zhao, Zhiyu Chen, Chengkun Yang, Ziyue Huang, Jiaqi Liu, Fusheng Liu, Yang Zhou, Xiaojuan Wang, Zhongquan Sun, Shiyun Bao, Xiaojun Wang, Ming Yang, Guangxin Li, Bin Shu, Yong Liao, Hongxuan Li, Yao Tang, Shizhong Yang, Yongyi Zeng, Yufeng Yuan, Yinpeng Dong, Jihui Hao, Jun Zhu, Jiahong Dong

llms benchmarks

arXiv AI

Jul 10

When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability

arXiv:2607. 08535v1 Announce Type: cross Abstract: An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed.

By Zongyou Yang, Yinghan Hou, Xiaokun Yang

llms safety

arXiv AI

Jul 10

The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

arXiv:2607. 08734v1 Announce Type: new Abstract: Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity.

By Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung

llms efficiency

arXiv AI

Jul 10

Validity of LLMs as data annotators: AMALIA on authority

arXiv:2607. 08731v1 Announce Type: cross Abstract: A national language model offers a linguistic community its own instrument for measuring what its citizens say and value.

By Manuel Pita

llms benchmarks

arXiv Machine Learning

Jul 10

TTHE: Test-Time Harness Evolution

arXiv:2607. 08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures.

By Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai, Dahai Yu, Yike Guo, Xinmei Tian, Bo Han

llms agents data-engineering

arXiv AI

Jul 10

Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench

arXiv:2607. 08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them.

By Siddhartha Jain, Ameya Velingker

llms nlp benchmarks

arXiv AI

Jul 10

Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE

arXiv:2607. 07740v1 Announce Type: cross Abstract: Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasoning and tool traces routinely push the input an order of magnitude past the pretraining window, making zero-shot context extension the dominant deployment path for open-weight checkpoints.

By Haozhan Tang, Zerui Wang, Yuxian Gu, Song Han, Han Cai

llms rag agents efficiency benchmarks

arXiv AI

Jul 10

LLT: Local Linear Transformer for PDE Operator Learning

arXiv:2607. 07718v1 Announce Type: cross Abstract: Neural operators have become a common approach for learning PDE solution maps and accelerating numerical simulations.

By Oded Ovadia, Eli Turkel

llms safety

arXiv AI

Jul 10

Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting

arXiv:2607. 07858v1 Announce Type: new Abstract: Artificial intelligence (AI) is beginning to reshape actuarial practice, particularly in domains that require reasoning over unstructured documents, heterogeneous data sources, and regulated decision workflows.

By Robert Richardson, Josh Meyers, Brian Hartman, David Sandberg

llms rag agents

arXiv AI

Jul 10

From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents

arXiv:2607. 08028v1 Announce Type: new Abstract: Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context.

By Joongho Ahn, Moonsoo Kim

llms agents benchmarks safety

arXiv AI

Jul 10

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

arXiv:2607. 07976v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs).

By Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang, Hoang Anh Duy Le, Zhaozhuo Xu, Guanchu Wang, Vladimir Braverman

llms reinforcement-learning benchmarks

arXiv AI

Jul 10

From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure

arXiv:2607. 08288v1 Announce Type: cross Abstract: In critical infrastructure, operational technology environments often cannot be actively scanned, and yet active system feedback is needed for risk assessment and compliance.

By Lea Roxanne Muth, Marian Margraf

llms agents safety

arXiv AI

Jul 10

Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs

arXiv:2607. 08193v1 Announce Type: cross Abstract: Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills.

By Lorenzo Pant\`e, Andrea Fanti, Roberto Capobianco

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

Jul 10

Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing

arXiv:2607. 08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing.

By Feng Wang, Canmiao Fu, Zhipeng Huang, Chen Li, Jing Lyu, Ge Li

llms agents diffusion reinforcement-learning multimodal benchmarks

arXiv AI

Jul 10

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

arXiv:2607. 08143v1 Announce Type: cross Abstract: We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents.

By Maud Ehrmann, Emanuela Boros, Juri Opitz, Andrianos Michail, Florian Wagner, Simon Clematide

llms computer-vision fine-tuning

arXiv AI

Jul 10

A Multi-cluster Boundary Learning Method for Out-of-Scope Intent Detection via MiniLM Embedding

arXiv:2607. 07974v1 Announce Type: cross Abstract: Intent detection is a critical task that bridges human intents and system actions in human-machine interaction systems.

By Yihong Xu, Mingyu Kang, Linyuan L\"u

llms rag benchmarks

arXiv Machine Learning

Jul 10

The Proxy Presumption: From Semantic Embeddings to Valid Social Measures

arXiv:2605. 07409v2 Announce Type: replace-cross Abstract: Natural Language Processing is rapidly evolving into a primary instrument for Computational Social Science, with researchers increasingly using embeddings to measure latent constructs such as novelty, creativity, and bias.

By Baishi Li, Ta Yu, Kelvin J. L. Koa, Ke-Wei Huang

llms rag nlp safety

arXiv AI

Jul 10

When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals

arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.

By Kaihua Ding

llms safety

Get the daily briefing