语言大模型 / LLM - arXivDaily 专题

2509.23558 2025-09-30 cs.AI cs.CR 85%

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning

Zhaoqi Wang, Daqing He, Zijian Zhang, Xin Li, Liehuang Zhu, Meng Li, Jiamou Liu

机构 * Beijing Institute of Technology（北京理工大学）； Hefei University of Technology（合肥工业大学）； The University of Auckland（奥克兰大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2507.20849 2025-09-23 cs.CL 85%

Latent Inter-User Difference Modeling for LLM Personalization

Yilun Qiu, Tianhao Shi, Xiaoyan Zhao, Fengbin Zhu, Yang Zhang, Fuli Feng

机构 * National University of Singapore（新加坡国立大学）； University of Science and Technology of China（中国科学技术大学）； The Chinese University of Hong Kong（香港中文大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 2025 EMNLP Main Conference (Oral)

2509.14723 2025-09-19 cs.LG 85%

Transcoder-based Circuit Analysis for Interpretable Single-Cell Foundation Models

Sosuke Hosokawa, Toshiharu Kawakami, Satoshi Kodera, Masamichi Ito, Norihiko Takeda

机构 * The University of Tokyo（东京大学）； The University of Tokyo Hospital（东京大学医院）

专题命中其他LLM ：foundation model(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2509.13326 2025-09-18 cs.HC cs.LG 85%

LLM Chatbot-Creation Approaches

Hemil Mehta, Tanvi Raut, Kohav Yadav, Edward F. Gehringer

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Forthcoming in Frontiers in Education (FIE 2025), Nashville, Tennessee, USA, Nov 2-5, 2025

2509.04537 2025-09-18 cs.MA cs.AI cs.CY 85%

Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem

Ryosuke Takata, Atsushi Masumori, Takashi Ikegami

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.12591 2025-09-17 cs.CL 85%

MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models

Vijay Govindarajan, Pratik Patel, Sahil Tripathi, Md Azizul Hoque, Gautam Siddharth Kashyap

机构 * Expedia Group, USA（Expedia集团）； California Universities of Management and Sciences, USA（加州管理与科学大学）； Jamia Hamdard, New Delhi, India（贾迈亚哈曼德大学）； Macquarie University, Sydney, Australia（麦考瑞大学）

专题命中其他LLM ：prompting(title)；LLM(abstract)；large language model(abstract)；language model(abstract)

Comments Accepted in The 26th International Conference on Web Information Systems Engineering (WISE), scheduled for 15-17 December 2025 in Marrakech, Morocco

2509.09112 2025-09-16 cs.CR cs.AI 85%

Character-Level Perturbations Disrupt LLM Watermarks

Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang, He Zhang, Shirui Pan, Bo Liu, Asif Qumer Gill, Leo Yu Zhang

机构 * University of Technology Sydney（新南威尔士大学）； Griffith University（格里菲斯大学）； RMIT University（皇家墨尔本理工大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments accepted by Network and Distributed System Security (NDSS) Symposium 2026

Journal ref Network and Distributed System Security (NDSS) Symposium 2026

2509.10540 2025-09-16 cs.CR cs.AI 85%

EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Pavan Reddy, Aditya Sanjay Gujral

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 8 pages content, 1 page references, 2 figures, Published at AAAI Fall Symposium Series 2025

2509.09690 2025-09-15 cs.IR cs.LG 85%

Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systems

Ping Liu, Jianqiang Shen, Qianqi Shen, Chunnan Yao, Kevin Kao, Dan Xu, Rajat Arora, Baofen Zheng, Caleb Johnson, Liangjie Hong, Jingwei Wu, Wenjing Zhang

机构 * LinkedIn Corporation（LinkedIn公司）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments CIKM2025

2509.08858 2025-09-15 cs.CY cs.LG 85%

Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation

Oriane Peter, Kate Devlin

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted at AIES 2025

2509.07983 2025-09-15 q-bio.BM cs.LG 85%

Steering Protein Language Models

Long-Kai Huang, Rongyi Zhu, Bing He, Jianhua Yao

机构 * Tencent AI Lab（腾讯人工智能实验室）

专题命中其他LLM ：language model(title,abstract)；large language model(abstract)；foundation model(abstract)；分类 cs.LG

Comments Accepted to ICML 2025

2509.02896 2025-09-15 cs.DB cs.AI 85%

Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees

Sepanta Zeighami, Shreya Shankar, Aditya Parameswaran

机构 * UC Berkeley（伯克利大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments To appear in SIGMOD'26

2504.15546 2025-09-15 cs.SE cs.AI 85%

A Framework for Testing and Adapting REST APIs as LLM Tools

Jayachandu Bandlamudi, Ritwik Chaudhuri, Neelamadhav Gantayat, Sambit Ghosh, Kushal Mukherjee, Prerna Agarwal, Renuka Sindhgatta, Sameep Mehta

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2502.08395 2025-09-11 cs.CL 85%

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance

Paul Röttger, Musashi Hinck, Valentin Hofmann, Kobi Hackenburg, Valentina Pyatkin, Faeze Brahman, Dirk Hovy

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments accepted at TACL (pre-MIT Press publication version)

2509.05338 2025-09-09 cs.RO cs.AI 85%

Plantbot: Integrating Plant and Robot through LLM Modular Agent Networks

Atsushi Masumori, Norihiro Maruyama, Itsuki Doi, johnsmith, Hiroki Sato, Takashi Ikegami

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2507.02436 2025-09-03 cs.CE cs.AI physics.optics 85%

Toward a Robust and Generalizable Metamaterial Foundation Model

Namjung Kim, Dongseok Lee, Jongbin Yu, Sung Woong Cho, Dosung Lee, Yesol Park, Youngjoon Hong

专题命中其他LLM ：foundation model(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.00622 2025-09-03 cs.AI cs.IR 85%

BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting

Shiqiao Zhou, Holger Schöner, Huanbo Lyu, Edouard Fouché, Shuo Wang

机构 * University of Birmingham（伯明翰大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2504.11497 2025-09-03 cs.LG cs.AR 85%

LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit

Chang Liu, Emmanuel A. Olowe, Danial Chitnis

机构 * School of Engineering The University of Edinburgh Edinburgh, UK（工程学院皇家爱丁堡大学英国爱丁堡）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments to be presented in IEEE NEWCAS 2025

Journal ref 2025 23rd IEEE Interregional NEWCAS Conference (NEWCAS)

2502.11649 2025-09-03 cs.AI cs.SI 85%

Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation

Amin Qasmi, Usman Naseem, Mehwish Nasim

机构 * The University of Western Australia（西澳大学）； Lahore University of Management Sciences（拉合尔管理科学大学）； Macquarie University（麦考瑞大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2402.14533 2025-09-03 cs.CL 85%

Whose LLM is it Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard

Ariel Rosenfeld, Teddy Lazebnik

机构 * Department of Information Science（信息科学系）； Bar Ilan University（巴伊兰大学）； Department of Information Systems（信息系统系）； University of Haifa（海法大学）； Department of Computing（计算机系）； Jonkoping University（约翰·科普林大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2508.21628 2025-09-01 cs.CL cs.HC 85%

Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks

Sarfaroz Yunusov, Kaige Chen, Kazi Nishat Anwar, Ali Emami

机构 * Brock University（布鲁克大学）； Emory University（埃默里大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 Main Conference

2508.19558 2025-08-28 cs.SE cs.CL cs.PL 85%

Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking

Zhuohao Li, Wenqing Chen, Jianxing Yu, Zhichao Lu

机构 * School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）； School of Software Engineering, Sun Yat-Sen University（中山大学软件工程学院）； School of Artificial Intelligence, Sun Yat-Sen University（中山大学人工智能学院）； Key Laboratory of Sustainable Tourism Smart Assessment Technology, Ministry of Culture and Tourism of China（文化和旅游部可持续旅游智能评估技术重点实验室）； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2508.19288 2025-08-28 cs.CR cs.AI 85%

Tricking LLM-Based NPCs into Spilling Secrets

Kyohei Shiomi, Zhuotao Lian, Toru Nakanishi, Teruaki Kitasuka

机构 * Hiroshima University（广岛大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2508.19287 2025-08-28 cs.CR cs.AI 85%

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

Zhuotao Lian, Weiyu Wang, Qingkui Zeng, Toru Nakanishi, Teruaki Kitasuka, Chunhua Su

机构 * Graduate School of Advanced Science and Engineering（先进科学与工程研究生学校）； Hiroshima University（广岛大学）； Graduate School of Science and Engineering（科学与工程研究生学校）； Hosei University（立命馆大学）； School of Mathematics and Computer Science（数学与计算机科学学院）； Tongling University（铜陵大学）； School of Computer Science and Engineering（计算机科学与工程学院）； University of Aizu（立海大学）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2502.09787 2025-08-27 cs.SE cs.AI cs.HC 85%

TableTalk: Scaffolding Spreadsheet Development with a Language Agent

Jenny T. Liang, Aayush Kumar, Yasharth Bajpai, Sumit Gulwani, Vu Le, Chris Parnin, Arjun Radhakrishna, Ashish Tiwari, Emerson Murphy-Hill, Guastavo Soares

机构 * Carnegie Mellon University（卡内基梅隆大学）； Microsoft（微软）

专题命中其他LLM ：language agent(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2407.08249 2025-08-27 cs.NI cs.AI 85%

GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration

Beni Ifland, Elad Duani, Rubin Krief, Miro Ohana, Aviram Zilberman, Andres Murillo, Ofir Manor, Ortal Lavi, Hikichi Kenji, Asaf Shabtai, Yuval Elovici, Rami Puzis

机构 * 1 Ben Gurion University of the Negev, Software

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2508.15848 2025-08-25 cs.CR cs.CL 85%

Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion

Yinghan Zhou, Juan Wen, Wanli Peng, Zhengxian Wu, Ziwei Zhang, Yiming Xue

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2403.17983 2025-08-21 cs.CR cs.LG 85%

Is The Watermarking Of LLM-Generated Code Robust?

Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； VMware Research（VMware研究）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

2508.13975 2025-08-20 cs.AI 85%

ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation

Jingquan Wang, Andrew Negrut, Harry Zhang, Khailanii Slaton, Shu Wang, Radu Serban, Jinlong Wu, Dan Negrut

机构 * Department of Mechanical Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校机械工程系）； Department of Computer Science, Rice University（里德大学计算机科学系）

专题命中其他LLM ：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.AI

2508.12555 2025-08-19 cs.LG 85%

Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement

Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Mahashweta Das

机构 * Visa Research（Visa研究）

专题命中其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 11 pages, 10 figures

1. 其他LLM 12251 篇

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning

Latent Inter-User Difference Modeling for LLM Personalization

Transcoder-based Circuit Analysis for Interpretable Single-Cell Foundation Models

LLM Chatbot-Creation Approaches

Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem

MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models

Character-Level Perturbations Disrupt LLM Watermarks

EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systems

Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation

Steering Protein Language Models

Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees

A Framework for Testing and Adapting REST APIs as LLM Tools

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance

Plantbot: Integrating Plant and Robot through LLM Modular Agent Networks

Toward a Robust and Generalizable Metamaterial Foundation Model

BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting

LLM-based AI Agent for Sizing of Analog and Mixed Signal Circuit

Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation

Whose LLM is it Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard

Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks

Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking

Tricking LLM-Based NPCs into Spilling Secrets

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior

TableTalk: Scaffolding Spreadsheet Development with a Language Agent

GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration

Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion

Is The Watermarking Of LLM-Generated Code Robust?

ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation

Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement