Large language models

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

31,067 stories · RSS feed

arXiv Machine Learning

Jun 9

Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models

arXiv:2606. 07522v1 Announce Type: cross Abstract: We propose an unsupervised method of resolving slang, unique entities, and folklore from online communities by isolating words in the lexicon that have the highest magnitude of semantic shift.

By Julia Kruk, Sanchita Porwal, Amitrajit Bhattacharjee, Mansi Phute

llms fine-tuning

arXiv AI

Jun 9

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

arXiv:2605. 11855v2 Announce Type: replace-cross Abstract: Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance.

By Julien Brandoit, Arthur Fyon, Damien Ernst, Guillaume Drion

llms efficiency benchmarks

arXiv AI

Jun 9

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression

arXiv:2605. 25085v2 Announce Type: replace-cross Abstract: We study the rate-distortion limits of online KV cache compression in autoregressive language models, formulating it as sequential Wyner-Ziv source coding on the filtration induced by the model, with the next-step query as decoder side information.

By Munsik Kim

llms efficiency benchmarks

arXiv AI

Jun 9

MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance

arXiv:2605. 22664v2 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions.

By Thomson Yen, Julian Poeltl, Harshith Srinivas Gear, Yilin Meng, Joshua Fan, Adam Shen, Yili Liu, Ali Bauyrzhan, Siri Du, Haoyang Liu, Daniel Guetta, Hongseok Namkoong

llms agents benchmarks

arXiv Machine Learning

Jun 9

QueryWeaver: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation

arXiv:2606. 08300v1 Announce Type: new Abstract: Many real-world queries over personal data span multiple applications and require structured planning, as individual tools expose only partial information.

By Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng Chau

llms agents

arXiv AI

Jun 9

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

arXiv:2606. 07591v1 Announce Type: cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.

By Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao, Yixin Chen, Hengjian Gao, Yiheng Wang, Qi Li, Kun Li, Sheng Xu, Shengdu Chai, Fangchen Yu, Xiangyu Zhao, Zhangrui Zhao, Weijie Ma, Zijie Guo, Haoyu Zhou, Haoxiang Yin, Lixue Cheng, Chaofan Hu, Haoxuan Li, Lu Mi, Xuxuan Xie, Yifan Zhou, Ruizhe Chen, Zhiwang Zhou, Xingjian Guo, Yuhao Zhou, Xuming He, Shengyuan Xu, Xinyu Gu, Jiamin Wu, Mianxin Liu, Chunfeng Song, Fenghua Ling, Dongzhan Zhou, Shixiang Tang, Yuqiang Li, Mao Su, Peng Ye, Siqi Sun, Bin Wang, Xue Yang, Zhenfei Yin, Tianfan Fu, Guangtao Zhai, Wanli Ouyang, Bo Zhang, Lei Bai, Wenlong Zhang

llms agents multimodal benchmarks

arXiv Machine Learning

Jun 9

PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning

arXiv:2606. 09301v1 Announce Type: new Abstract: Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images.

By Zekai Chen, Miao Zhang, Jiayang Xing, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang

llms multimodal benchmarks

arXiv Machine Learning

Jun 9

Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning

arXiv:2606. 09289v1 Announce Type: new Abstract: Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases.

By Yuesen Li, Daniel Link

llms diffusion computer-vision

arXiv Machine Learning

Jun 9

In-Context Learning for Latent Space Bayesian Optimization

arXiv:2606. 09664v1 Announce Type: new Abstract: Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins.

By Tuan A. Vu, Harri L\"ahdesm\"aki, Julien Martinelli

llms diffusion benchmarks

arXiv AI

Jun 9

Some hypotheses on how chatbots work in problem-solving-driven conversations. Large Language Models as confirmation of the Innovation Illusion

arXiv:2606. 07722v1 Announce Type: new Abstract: This article offers a perspective on the nature of chatbots as genuine conversation partners when discussing problems in relation to their solutions.

By S. F. M. van Vlijmen, H. D. Lethe jr

llms

arXiv Machine Learning

Jun 9

Can LLMs extract scientific consensus? A case study in high-temperature superconductivity

arXiv:2606. 07570v1 Announce Type: cross Abstract: Scientific knowledge is increasingly dispersed across vast and heterogeneous scientific literature, where important claims are often implicit, evolving, and internally debated.

By Mouyang Cheng, Wenhao He, Zhuotao Jin, Bowen Yu, Ju Li, Boris Kozinsky, Yao Wang, Pavel Volkov, Liangzi Deng, Ching-Wu Chu, Xiao-Gang Wen, Mingda Li

llms nlp benchmarks

arXiv AI

Jun 9

From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs

arXiv:2606. 07586v1 Announce Type: cross Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on such hardware remains labor-intensive.

By Jiajie Li, Erwei Wang, Zhiru Zhang, Samuel Bayliss

llms agents

arXiv Machine Learning

Jun 9

Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction

arXiv:2606. 08147v1 Announce Type: cross Abstract: DNA cis-regulatory elements (CREs) such as enhancers control gene expression levels.

By Yi Duan, Zhao Yang, Jiwei Zhu, Ying Ba, Chuan Cao, Bing Su

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 9

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

arXiv:2606. 09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.

By Xiaofeng Lin, Yukai Yang, Daniel Guo, Sahil Arun Nale, Charles Fleming, Guang Cheng

llms agents benchmarks safety

arXiv AI

Jun 9

DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs

arXiv:2601. 07994v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.

By Nayoung Choi, Jonathan Zhang, Jinho D. Choi

llms efficiency benchmarks

arXiv AI

Jun 9

Adversarial Robustness of Activation Steering in Large Language Models

arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.

By Kien Le, Thai Le

llms safety

arXiv AI

Jun 9

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

arXiv:2606. 07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility.

By Yuhuan Yuan, Zhouliang Yu, Minghao Liu, Weiyang Liu, Ge Lin Kan

llms reinforcement-learning safety

arXiv AI

Jun 9

Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP

arXiv:2505. 11189v3 Announce Type: replace Abstract: Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs.

By Francesco Sovrano

llms

arXiv AI

Jun 9

Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks

arXiv:2604. 19755v2 Announce Type: replace Abstract: Anti-money laundering (AML) transaction monitoring generates large volumes of alerts that must be rapidly triaged by investigators under strict audit and governance constraints.

By Dorothy Torres, Wei Cheng, Ke Hu

llms rag benchmarks safety

arXiv Machine Learning

Jun 9

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.

By Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut

llms agents benchmarks safety

Get the daily briefing