语言大模型 / LLM - arXivDaily 专题

2412.18750 2025-09-30 cs.SE cs.AI cs.LG 90%

Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localization

Md Nakhla Rafi, Dong Jae Kim, Tse-Hsun Chen, Shaowei Wang

机构 * Software Performance, Analysis, \ Reliability (SPEAR) Lab\ University Montreal Canada ； DePaul University Chicago USA ； University of Manitoba Winnipeg Canada ； Software Performance, Analysis, \ Reliability (SPEAR) Lab\ University ； DePaul University ； University of Manitoba

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

2509.25043 2025-09-30 cs.SE cs.AI 89%

Large Language Models for Software Testing: A Research Roadmap

Cristian Augusto, Antonia Bertolino, Guglielmo De Angelis, Francesca Lonetti, Jesús Morán

机构 * University of Oviedo（奥维多大学）

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

Comments 40 pages & 10 figures Submitted on 29th September 2025

2509.23972 2025-09-30 cs.AR 88%

AssertFix: Empowering Automated Assertion Fix via Large Language Models

Hongqin Lyu, Yunlin Du, Yonghao Wang, Zhiteng Chao, Tiancheng Wang, Huawei Li

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

Comments 6 pages, 6 figures

2507.23284 2025-09-30 cs.CV 88%

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Dohwan Ko, Ji Soo Lee, Minhyuk Choi, Zihang Meng, Hyunwoo J. Kim

机构 * Korea University（韩国大学）； Meta GenAI（Meta 生成人工智能）； KAIST（韩国科学技术院）

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

Comments ICCV 2025 Highlight

2501.05625 2025-09-30 cs.SE 88%

Harnessing Large Language Model for Virtual Reality Exploration Testing: A Case Study

Zhenyu Qi, Haotang Li, Hao Qin, Kebin Peng, Sen He, Xue Qin

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

Journal ref Automated Software Engineering, 33, 7 (2026)

2407.16994 2025-09-30 cs.AI cs.CL cs.LG 87%

A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs

Jake R. Watts, Joel Sokol

机构 * Department of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA（工业与系统工程系，佐治亚理工学院，亚特兰大，佐治亚州，美国）

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

Comments 7 pages, 2 figures

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

2509.24043 2025-09-30 cs.CR 85%

An Ensemble Framework for Unbiased Language Model Watermarking

Yihan Wu, Ruibo Chen, Georgios Milis, Heng Huang

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

2509.22978 2025-09-30 cs.SE 85%

Towards Human-interpretable Explanation in Code Clone Detection using LLM-based Post Hoc Explainer

Teeradaj Racharak, Chaiyong Ragkhitwetsagul, Chayanee Junplong, Akara Supratak

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

2503.23718 2025-09-30 cs.SE cs.CR 85%

PROMFUZZ: Leveraging LLM-Driven and Bug-Oriented Composite Analysis for Detecting Functional Bugs in Smart Contracts

Xingshuang Lin, Qinge Xie, Binbin Zhao, Yuan Tian, Saman Zonouz, Na Ruan, Jiliang Li, Raheem Beyah, Shouling Ji

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

2509.23630 2025-09-30 cs.AI 83%

Game-Oriented ASR Error Correction via RAG-Enhanced LLM

Yan Jiang, Yongle Luo, Qixian Zhou, Elvis S. Liu

机构 * Tencent Games（腾讯游戏）

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

Journal ref 2025 IEEE Conference on Games (CoG), Lisbon, Portugal, 2025, pp. 1-8

2509.23204 2025-09-30 cs.CL 79%

Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2

Stefan Arnold, René Gröbner

机构 * Friedrich-Alexander-Universität Erlangen-Nürnberg（埃朗根-纽伦堡弗里德里希-亚历山大大学）

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

2509.24090 2025-09-30 cs.CL cs.AI 79%

Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?

Matteo Boffa, Jiaxuan You

机构 * Politecnico di Torino（托斯大学）； University of Urbana Champaign (UIUC)（乌尔班纳-香槟大学）

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

2501.19301 2025-09-30 cs.CL cs.AI 79%

Beyond checkmate: exploring the creative chokepoints in AI text

Nafis Irtiza Tripto, Saranya Venkatraman, Mahjabin Nahar, Dongwon Lee

机构 * The Pennsylvania State University（宾夕法尼亚州立大学）； Amazon（亚马逊公司）

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

Comments Accepted at 30th Conference on Empirical Methods in Natural Language Processing (EMNLP'25 Main conference). 9 pages

2508.18244 2025-09-30 cs.LG cs.AI 79%

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data

Chu-Cheng Lin, Daiyi Peng, Yifeng Lu, Ming Zhang, Eugene Ie

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

2507.20021 2025-09-30 cs.RO cs.AI cs.LG 79%

When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation

Matin Aghaei, Lingfeng Zhang, Mohammad Ali Alomrani, Mahdi Biparva, Yingxue Zhang

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

Comments Preprint; under peer review

2406.03614 2025-09-30 cs.LG cs.CL q-fin.RM 79%

Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs

Alexander Bakumenko, Kateřina Hlaváčková-Schindler, Claudia Plant, Nina C. Hubig

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

Journal ref IEEE Access 13 (2025) 146757-146771

2509.24807 2025-09-30 cs.CR 78%

Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts

Dong Hyun Roh, Rajesh Kumar

专题命中其他LLM ：LLM(title,abstract)

Comments Accepted for publication at IEEE-ICMLA 2025. Contains nine pages, six figures, and two tables

2509.24370 2025-09-30 cs.CV 78%

DINOReg: Strong Point Cloud Registration with Vision Foundation Model

Congjia Chen, Yufu Qu

机构 * School of Instrumentation and Optoelectronic Engineering（仪器与光电工程学院）

专题命中其他LLM ：foundation model(title,abstract)

2509.23991 2025-09-30 cs.CV 78%

RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization

Dongki Jung, Jaehoon Choi, Yonghan Lee, Dinesh Manocha

机构 * University of Maryland, College Park（马里兰大学 College Park 分校）

专题命中其他LLM ：foundation model(title,abstract)

2507.04511 2025-09-30 cs.CV 78%

FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection

Xinhua Lu, Runhe Lai, Yanqi Wu, Kanghao Chen, Wei-Shi Zheng, Ruixuan Wang

机构 * Sun Yat-sen University（中山大学）； Peng Cheng Laboratory（鹏城实验室）； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Key Laboratory of Machine Intelligence and Advanced Computing（人工智能与先进计算重点实验室）

专题命中其他LLM ：language model(title,abstract)

Comments 12 pages, 4 figures, Accepted by ICCV2025

2509.21839 2025-09-30 cs.CV cs.AI 77%

DiTraj: training-free trajectory control for video diffusion transformer

Cheng Lei, Jiayu Zhang, Yue Ma, Xinyu Wang, Long Chen, Liang Tang, Yiqiang Yan, Fei Su, Zhicheng Zhao

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； Lenovo（联想）； HKUST（香港科技大学）； Tsinghua University（清华大学）

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

2509.24024 2025-09-30 cs.FL cs.CL cs.LG cs.LO 73%

The Role of Logic and Automata in Understanding Transformers

Anthony W. Lin, Pablo Barcelo

机构 * Max-Planck Institute for Software Systems, Kaiserslautern, Germany University of Kaiserslautern-Landau, Kaiserslautern, Germany Institute for Mathematical

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

Comments Preprint of invited paper for RP'25

2506.17881 2025-09-30 cs.CL cs.AI 73%

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Hua Tang, Lingyong Yan, Yukun Zhao, Shuaiqiang Wang, Jizhou Huang, Dawei Yin

机构 * The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））； Baidu Inc.（百度公司）

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

2412.01752 2025-09-30 cs.AI cs.CL 73%

A Neurosymbolic Fast and Slow Architecture for Graph Coloring

Vedant Khandelwal, Vishal Pallagani, Biplav Srivastava, Francesca Rossi

机构 * University of South Carolina（南卡罗来纳大学）； IBM Research（IBM研究院）

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

Comments 31 Pages, 18 Figures, 3 Tables

2506.17144 2025-09-30 cs.CV cs.AI cs.LG 73%

Do We Need Large VLMs for Spotting Soccer Actions?

Ritabrata Chakraborty, Rajatsubhra Chakraborty, Avijit Dasgupta, Sandeep Chaurasia

机构 * Manipal University Jaipur（贾浦尔曼普尔大学）； UNC–Charlotte（北卡罗来纳州立大学夏洛特分校）； IIIT Hyderabad（海得拉巴印度理工学院）

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

Comments 6 pages, 2 tables

2509.24216 2025-09-30 cs.CL cs.CY 70%

MoVa: Towards Generalizable Classification of Human Morals and Values

Ziyu Chen, Junfei Sun, Chenxi Li, Tuan Dung Nguyen, Jing Yao, Xiaoyuan Yi, Xing Xie, Chenhao Tan, Lexing Xie

机构 * The Australian National University（澳大利亚国立大学）； University of Chicago（芝加哥大学）； University of Pennsylvania（宾夕法尼亚大学）； Microsoft Research Asia（微软亚洲研究院）

专题命中其他LLM ：LLM(abstract)；prompting(abstract)；分类 cs.CL

Comments 9 pages, 10 figures and tables, EMNLP 2025 main conference

2507.23512 2025-09-30 cs.LG math.OC 70%

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

Saleh Vatan Khah, Savelii Chezhegov, Shahrokh Farahmand, Samuel Horváth, Eduard Gorbunov

机构 * IUST（伊朗伊斯兰科技与应用大学）； MBZUAI（马尔代夫人工智能研究所）

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

Comments 60 pages

2505.20817 2025-09-30 math.OC cs.LG 70%

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise

Savelii Chezhegov, Aleksandr Beznosikov, Samuel Horváth, Eduard Gorbunov

机构 * MCAS（麦吉尔-西奈大学（McGill-Sinai Academy））； MBZUAI（穆罕默德·本·拉希德智能研究院（MBZUAI））

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

Comments 33 pages

2402.00689 2025-09-30 cs.CR cs.AI 70%

Ocassionally Secure: A Comparative Analysis of Code Generation Assistants

Ran Elgedawy, Porter Dosch, John Sadik, Senjuti Dutta, Anuj Gautam, Konstantinos Georgiou, Farzin Gholamrezae, Fujiao Ji, Kyungchan Lim, Qian Liu, Scott Ruoti

机构 * OpenAI ； Google（谷歌）； DeepSeek

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

Comments 12 pages, 2 figures

1. 其他LLM 42 篇

Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localization

Large Language Models for Software Testing: A Research Roadmap

AssertFix: Empowering Automated Assertion Fix via Large Language Models

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Harnessing Large Language Model for Virtual Reality Exploration Testing: A Case Study

A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning

An Ensemble Framework for Unbiased Language Model Watermarking

Towards Human-interpretable Explanation in Code Clone Detection using LLM-based Post Hoc Explainer

PROMFUZZ: Leveraging LLM-Driven and Bug-Oriented Composite Analysis for Detecting Functional Bugs in Smart Contracts

Game-Oriented ASR Error Correction via RAG-Enhanced LLM

Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2

Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?

Beyond checkmate: exploring the creative chokepoints in AI text

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data

When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation

Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs

Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts

DINOReg: Strong Point Cloud Registration with Vision Foundation Model

RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization

FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection

DiTraj: training-free trajectory control for video diffusion transformer

The Role of Logic and Automata in Understanding Transformers

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication

A Neurosymbolic Fast and Slow Architecture for Graph Coloring

Do We Need Large VLMs for Spotting Soccer Actions?

MoVa: Towards Generalizable Classification of Human Morals and Values

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise

Ocassionally Secure: A Comparative Analysis of Code Generation Assistants