Large language models

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

25,737 stories · RSS feed

arXiv AI

Jun 30

Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

arXiv:2606. 28770v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated the ability to simulate human-like OCEAN personality traits in generated text.

By David Courtis, Ting Hu

llms fine-tuning benchmarks safety

arXiv AI

Jun 30

Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation

arXiv:2606. 28593v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) have achieved significant improvements on static visual-to-code tasks such as generating code for webpages, charts, or SVGs, it remains unclear whether they can recover temporal dynamics when motion is present.

By Anya Ji, Abhijith Varma Mudunuri, David M. Chan, Alane Suhr

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 30

SemJoin: Semantic Join Optimization

arXiv:2606. 29532v1 Announce Type: cross Abstract: Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis.

By Christopher Gou, Aditya Banerjee, Jiaxuan Wang, Chunwei Liu

llms rag agents

arXiv AI

Jun 30

Online Data Selection for Instruction Tuning via Gaussian Processes

arXiv:2606. 30077v1 Announce Type: cross Abstract: With Large Language Model (LLM) pre-training and fine-tuning shifting its focus from data volume to data quality, quality data selection has emerged as a critical research topic.

By Jun Wang, Quoc Phong Nguyen, Julien Monteil, Vu Nguyen

llms fine-tuning benchmarks data-engineering

arXiv AI

Jun 30

ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval

arXiv:2606. 28326v1 Announce Type: cross Abstract: This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries.

By Ke Chen, Shengyuan Han, Yongfeng Huang, Yujin Zhu, Jingwei Xiong, Liang Xu, Jundong Liu

llms agents benchmarks

arXiv Machine Learning

Jun 30

Uncertainty-Aware Generation and Decision-Making Under Ambiguity

arXiv:2606. 30578v1 Announce Type: cross Abstract: With rapidly improving capabilities, Large Language Models (LLMs) are increasingly used in many complex real-world tasks.

By Nico Daheim, Iryna Gurevych

llms

arXiv Machine Learning

Jun 30

A Mechanistic Study of Transformers Training Dynamics

arXiv:2410. 24050v3 Announce Type: replace Abstract: Large-scale pretraining of transformers has been central to the success of foundation models.

By Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes

llms

arXiv AI

Jun 30

Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement

arXiv:2606. 29639v1 Announce Type: cross Abstract: Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models.

By Aunabil Chakma, Mihai Surdeanu, Eduardo Blanco

llms benchmarks

arXiv AI

Jun 30

CaveAgent: Transforming LLMs into Stateful Runtime Operators

arXiv:2601. 01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift.

By Maohao Ran, Zhenglin Wan, Cooper Lin, Yanting Zhang, Hongyu Xin, Hongwei Fan, Yibo Xu, Beier Luo, Yaxin Zhou, Wangbo Zhao, Lijie Yang, Lang Feng, Fuchao Yang, Jingxuan Wu, Yiqiao Huang, Chendong Ma, Yusen Huang, Dailing Jiang, Jianbo Deng, Sirui Han, Yang You, Bo An, Yike Guo, Jun Song

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 30

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

arXiv:2606. 28356v1 Announce Type: cross Abstract: Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems.

By Qianfeng Wen, Yifan Simon Liu, Xin Liu, Difan Jiao, Blair Yang, Junda Wu, Zhenwei Tang

llms agents

arXiv AI

Jun 30

Test-Time Detoxification without Training or Learning Anything

arXiv:2602. 02498v2 Announce Type: replace-cross Abstract: Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale.

By Baturay Saglam, Dionysis Kalogerias

llms rag safety

arXiv AI

Jun 30

Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off

arXiv:2603. 26815v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity.

By Zhiyuan Cheng, Longying Lai, Yue Liu

llms rag agents benchmarks

arXiv AI

Jun 30

When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries

arXiv:2606. 28332v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood.

By Yige Li, Jun Sun, Wei Zhao, Zhe Li, Yutao Wu, Hanxun Huang, Xiang Zheng, Xingjun Ma

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 30

Generative Learning as a Tool to Improve Perception of Emotional Body Motion Expressions

arXiv:2606. 28769v1 Announce Type: new Abstract: Emotional body motion expressions are an essential element of non-verbal communication.

By Huakun Liu, Miao Cheng, Xin Wei, Felix Dollack, Victor Schneider, Hideaki Uchiyama, Chia-huei Tseng, Yoshifumi Kitamura, Monica Perusquia-Hernandez

llms robotics safety

arXiv Machine Learning

Jun 30

RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering

arXiv:2606. 30380v1 Announce Type: cross Abstract: We present RenderFormer++, a scalable and physically grounded feed-forward neural rendering framework for global illumination in mesh scenes.

By Huangsheng Du, Haoran Zhu, Youcheng Cai, Jinyang Meng, Ligang Liu

llms nlp

arXiv AI

Jun 30

HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval

arXiv:2606. 28336v1 Announce Type: cross Abstract: Methodology Inspiration Retrieval (MIR) asks a system to retrieve prior papers whose methods can inspire a new research proposal.

By Yang Yang, Boyun Xu, Hao Fu, Jindong Li, Zining Zhong, Bowen Tian, Jiemin Wu, Menglin Yang, Yutao Yue

llms benchmarks

arXiv AI

Jun 30

ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services

arXiv:2606. 28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy.

By Kuan Yan, Zhiqing Tang, Tian Wang, Weijia Jia

llms rag nlp efficiency

arXiv AI

Jun 30

The strength of clinical evidence is recoverable from language model representations but not from their stated grades

arXiv:2606. 29034v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported.

By Soroosh Tayebi Arasteh

llms

arXiv AI

Jun 30

When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

arXiv:2606. 28438v1 Announce Type: cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control.

By Xinyuan Song, Zekun Cai, Liang Zhao

llms fine-tuning benchmarks

arXiv AI

Jun 30

Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data

arXiv:2606. 30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias.

By Haobo Yang

llms safety

Get the daily briefing