arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

2025-09-23 至 2025-09-23 共收录 350 信号源:cs.CL, cs.AI, cs.LG

1. 指令微调 33 篇

2509.16275 2025-09-23 cs.CR cs.AI cs.SE 87%

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair

Jugal Gajjar, Kamalasankari Subramaniakuppusamy, Relsy Puthal, Kaustik Ranaware

机构 * Computer Science Department(计算机科学系) Applied Economics Department(应用经济学系)

专题命中 指令微调 :LLM(title,abstract);large language model(abstract,comments);language model(abstract,comments);分类 cs.AI

Comments 6 pages, 3 figures, 4 tables, 1 algorithm, accepted in the Robustness and Security of Large Language Models (ROSE-LLM) special session at ICMLA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12244 2025-09-23 cs.CL 86%

Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce

Haojin Wang, Zining Zhu, Freda Shi

机构 * University of Waterloo(多伦多大学) Stevens Institute of Technology(史蒂文斯理工学院) Vector Institute, Canada CIFAR AI Chair(加拿大向量研究所)

专题命中 指令微调 :language model(title,abstract);prompting(title);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13222 2025-09-23 cs.CL cs.AI 84%

Can Language Models Follow Multiple Turns of Entangled Instructions?

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of California San Diego(加州大学圣地亚哥分校)

专题命中 指令微调 :language model(title,abstract);large language model(abstract);分类 cs.CL、cs.AI

Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16660 2025-09-23 cs.CL 83%

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation

Zuhair Hasan Shaik, Abdullah Mazhar, Aseem Srivastava, Md Shad Akhtar

机构 * IIIT Dharwad, India(印度IIIT达尔瓦德大学) IIIT Delhi, India(印度IIIT德里大学) FLaME-NLP Lab, IIIT Delhi(IIIT德里大学FLaME-NLP实验室)

专题命中 指令微调 :language model(title,abstract);large language model(abstract);分类 cs.CL

Comments Accepted to the NeurIPS 2025 Research Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.00251 2025-09-23 cs.AI cs.HC 83%

Fine-Tuning Open-Weight Language Models to Deliver Cognitive Behavioral Therapy for Depression: A Feasibility Study

Talha Tahir

机构 * Department of Psychiatry University of Toronto(精神病学系多伦多大学)

专题命中 指令微调 :language model(title,abstract);large language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14992 2025-09-23 cs.RO 82%

ExT: Towards Scalable Autonomous Excavation via Large-Scale Multi-Task Pretraining and Fine-Tuning

Yifan Zhai, Lorenzo Terenzi, Patrick Frey, Diego Garcia Soto, Pascal Egli, Marco Hutter

机构 * Robotic Systems Lab, ETH Zürich(苏黎世联邦理工学院机器人系统实验室)

专题命中 指令微调 :pretraining(title,abstract);SFT(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16508 2025-09-23 cs.LG 81%

Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever

Marijan Fofonjka, Shahryar Zehtabi, Alireza Behtash, Tyler Mauer, David Stout

机构 * webAI

专题命中 指令微调 :large language model(abstract);language model(abstract);small language model(abstract);SLM(abstract)

Comments 22 pages, 7 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13448 2025-09-23 cs.CL cs.AI 81%

CIE: Controlling Language Model Text Generations Using Continuous Signals

Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito

机构 * University of Maryland, College Park(马里兰大学 College Park分校) Carnegie Mellon University(卡内基梅隆大学)

专题命中 指令微调 :language model(title,abstract);分类 cs.CL、cs.AI

Comments EMNLP Main 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17167 2025-09-23 cs.CL 79%

SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis

Seungjun Yi, Joakim Nguyen, Huimin Xu, Terence Lim, Joseph Skrovan, Mehak Beri, Hitakshi Modi, Andrew Well, Liu Leqi, Mia Markey, Ying Ding

机构 * University of Texas at Austin(德克萨斯大学) Vanderbilt University School of Medicine(范德比大学医学院) McCombs School of Business University of Texas at Austin(德克萨斯大学麦康姆商学院)

专题命中 指令微调 :SFT(title,abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16617 2025-09-23 cs.CV cs.AI 79%

Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model

David Kreismann

机构 * Baden-Wuerttemberg Cooperative State University(巴登-符腾堡州立大学)

专题命中 指令微调 :foundation model(title,abstract);分类 cs.AI

Comments 12 pages, 4 figures, to appear in GI LNI (SKILL 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21535 2025-09-23 eess.IV cs.CV cs.LG 77%

Exploring the Design Space of 3D MLLMs for CT Report Generation

Mohammed Baharoon, Jun Ma, Congyu Fang, Augustin Toma, Bo Wang

机构 * Vector Institute for Artificial Intelligence(向量人工智能研究所) Department of Biomedical Informatics, Harvard Medical School(生物医学信息学系,哈佛医学院) Peter Munk Cardiac Centre, University Health Network(皮特·蒙克心脏中心,大学健康网络) Medical Biophysics, University of Toronto(医学生物物理系,多伦多大学) Department of Computer Science, University of Toronto(计算机科学系,多伦多大学) Department of Laboratory Medicine and Pathobiology, University of Toronto(实验室医学与病理学系,多伦多大学) AI Hub, University Health Network(人工智能中心,大学健康网络)

专题命中 指令微调 :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18093 2025-09-23 cs.CL cs.AI cs.LG 75%

SEQR: Secure and Efficient QR-based LoRA Routing

William Fleshman, Benjamin Van Durme

专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.12636 2025-09-23 cs.SE 75%

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

Boyang Yang, Haoye Tian, Jiadong Ren, Hongyu Zhang, Jacques Klein, Tegawendé F. Bissyandé, Claire Le Goues, Shunfu Jin

专题命中 指令微调 :LLM(abstract);large language model(abstract);language model(abstract)

Journal ref ACM Transactions on Software Engineering and Methodology, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11626 2025-09-23 cs.CL cs.AI 73%

Improving Instruct Models for Free: A Study on Partial Adaptation

Ozan İrsoy, Pengxiang Cheng, Jennifer L. Chen, Daniel Preoţiuc-Pietro, Shiyue Zhang, Duccio Pappadopulo

机构 * Bloomberg(贝莱德) Independent Researcher(独立研究者)

专题命中 指令微调 :instruction tuning(abstract);post-training(abstract);分类 cs.CL、cs.AI

Comments Author ordering chosen at random; accepted to EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16903 2025-09-23 cs.CL 70%

CLaC at DISRPT 2025: Hierarchical Adapters for Cross-Framework Multi-lingual Discourse Relation Classification

Nawar Turk, Daniele Comitogianni, Leila Kosseim

机构 * Computational Linguistics at Concordia (CLaC) Lab(康科迪亚大学计算语言学实验室) Dept. of Computer Science and Software Engineering(计算机科学与软件工程系) Concordia University(康科迪亚大学)

专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14646 2025-09-23 cs.CL 70%

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

Hengyuan Zhang, Xinrong Chen, Yingmin Qiu, Xiao Liang, Ziyue Li, Guanyu Wang, Weiping Li, Tong Mo, Hayden Kwok-Hay So, Ngai Wong

机构 * The University of Hong Kong(香港大学) Peking University(北京大学) Beijing University of Posts and Telecommunications(北京邮电大学) University of California, Los Angeles(加州大学洛杉矶分校) National Science Library, Chinese Academy of Sciences(中国科学院国家科学图书馆)

专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.CL

Comments Accepted by EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16422 2025-09-23 cs.CL 70%

Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning

Tom Mackintosh, Harish Tayyar Madabushi, Claire Bonial

机构 * University of Bath(巴斯大学) DEVCOM Army Research Laboratory(陆军研究实验室)

专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16788 2025-09-23 cs.CL cs.AI cs.LG 67%

Domain-Adaptive Pre-Training for Arabic Aspect-Based Sentiment Analysis: A Comparative Study of Domain Adaptation and Fine-Tuning Strategies

Salha Alyami, Amani Jamal, Areej Alhothali

机构 * Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziza University, Jeddah, Saudi Arabia(计算机科学系,计算与信息技术学院,国王阿卜杜勒阿齐兹大学,沙特阿拉伯吉达)

专题命中 指令微调 :language model(abstract);分类 cs.CL、cs.AI、cs.LG

Comments 26 excluding bibliography , journal article

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16628 2025-09-23 cs.CV 67%

Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning

Janak Kapuriya, Anwar Shaikh, Arnav Goel, Medha Hira, Apoorv Singh, Jay Saraf, Sanjana, Vaibhav Nauriyal, Avinash Anand, Zhengkui Wang, Rajiv Ratn Shah

机构 * Indraprastha Institute of Information Technology, Delhi(印度德里印度理工学院) Singapore Institute of Technology(新加坡理工学院)

专题命中 指令微调 :LLM(abstract);language model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17070 2025-09-23 cs.CR cs.CL cs.LG 62%

Localizing Malicious Outputs from CodeLLM

Mayukh Borana, Junyi Liang, Sai Sathiesh Rajan, Sudipta Chattopadhyay

机构 * Singapore University of Technology and Design(新加坡科技设计大学)

专题命中 指令微调 :LLM(abstract);分类 cs.CL、cs.LG

Comments 10 pages, 2 figures, 6 tables, Accepted at EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22118 2025-09-23 cs.CL 57%

Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches

Alan Ramponi, Marco Rovera, Robert Moro, Sara Tonelli

专题命中 指令微调 :LLM(abstract);分类 cs.CL

Comments Accepted to EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.15877 2025-09-23 cs.AI 57%

Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning

Simon Ouellette

机构 * Simon Ouellette

专题命中 指令微调 :LLM(abstract);分类 cs.AI

Comments this version fixes errors in AlphaEvolve total % calculation, Table 3 DSL description, and adds clarifications in response to review criticisms

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.09384 2025-09-23 cs.LG cs.CV 57%

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models

Lukas Thede, Karsten Roth, Olivier J. Hénaff, Matthias Bethge, Zeynep Akata

机构 * Tübingen AI Center, University of Tübingen(图宾根人工智能中心,图宾根大学) Helmholtz Munich, MCML(海德堡医学院,MCML) Google DeepMind(谷歌DeepMind) TU Munich(慕尼黑技术大学)

专题命中 指令微调 :foundation model(abstract);分类 cs.LG

Comments 3rd Conference on Lifelong Learning Agents (CoLLAs) 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16491 2025-09-23 cs.LG cs.CE 57%

FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG

Lovely Yeswanth Panchumarthi, Saurabh Kataria, Yi Wu, Xiao Hu, Alex Fedorov, Hyunjung Gloria Kwak

机构 * Computer Science Emory University(埃默里大学计算机科学系) School of Nursing Emory University(埃默里大学护理学院) Computer Science University of Oklahoma(俄克拉荷马大学计算机科学系)

专题命中 指令微调 :foundation model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.09372 2025-09-23 cs.RO 50%

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, Zirui Ge, Xinyang Tong, Wenxuan Song, Han Zhao, Wei Zhao, Pengxu Hou, Siteng Huang, Yifan Tang, Wenhui Wang, Ru Zhang, Jianyi Liu, Donglin Wang

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Westlake University(西湖大学) Zhejiang University(浙江大学) OpenHelix Team(OpenHelix团队) State Key Laboratory of Networking and Switching Technology(网络与交换技术国家重点实验室) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

专题命中 指令微调 :language model(abstract)

Comments 28 pages; Project page: https://vla-adapter.github.io/; Github: https://github.com/OpenHelix-Team/VLA-Adapter; HuggingFace: https://huggingface.co/VLA-Adapter

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05682 2025-09-23 cs.CV 50%

On the Suitability of Reinforcement Fine-Tuning to Visual Tasks

Xiaxu Chen, Wei Li, Chunxu Liu, Chi Xie, Xiaoyan Hu, Chengqian Ma, Feng Zhu, Rui Zhao

机构 * SenseTime Research(商汤科技研究院) Beijing Institute of Technology(北京理工大学) Nanjing University(南京大学) Tongji University(同济大学)

专题命中 指令微调 :SFT(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19269 2025-09-23 cs.CV 50%

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP

Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学) School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院) Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)

专题命中 指令微调 :language model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 后训练与偏好优化 17 篇

2502.13146 2025-09-23 cs.CV cs.LG 90%

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization

Shuo Xing, Peiran Li, Yuping Wang, Ruizheng Bai, Yueqi Wang, Chan-Wei Hu, Chengxuan Qian, Huaxiu Yao, Zhengzhong Tu

机构 * Texas A&M University(德克萨斯大学) University of Michigan(密歇根大学) UIUC(伊利诺伊大学香槟分校) UNC Chapel Hill(北卡罗来纳大学教堂山分校)

专题命中 后训练与偏好优化 :language model(title,abstract);preference optimization(title,abstract);large language model(abstract);RLHF(abstract)

Comments Published at EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04039 2025-09-23 cs.CV cs.AI cs.CL 90%

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization

Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao, Min Zhang

机构 * Soochow University(苏州大学) Baidu Inc.(百度公司) Shandong University(山东大学)

专题命中 后训练与偏好优化 :language model(title,abstract);preference optimization(title,abstract);large language model(abstract);分类 cs.CL、cs.AI

Comments This paper is accepted by EMNLP2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16475 2025-09-23 cs.LG cs.CL 88%

Towards Universal Debiasing for Language Models-based Tabular Data Generation

Tianchun Li, Tianci Liu, Xingchen Wang, Rongzhe Wei, Pan Li, Lu Su, Jing Gao

机构 * Purdue University(普渡大学) Georgia Institute of Technology(佐治亚理工学院)

专题命中 后训练与偏好优化 :language model(title,abstract);LLM(abstract);large language model(abstract);preference optimization(abstract)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏