语言大模型 / LLM

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, Lichao Sun

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Zhongguancun Academy（中关村学院） ； Shanghai Innovation Institute（上海创新研究院） ； Lehigh University（莱特大学） 纠错

专题命中 指令微调 ：post-training(title,abstract)；SFT(title,abstract)；LLM(title)；large language model(abstract)

Comments Accepted by NeurIPS 2025

Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds

Atij Mahesh

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 指令微调 ：large language model(title,abstract)；language model(title,abstract)；SFT(abstract)；preference optimization(abstract)

Comments 20 pages

Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models

Yan-Shuo Liang, Jia-Rui Chen, Wu-Jun Li

机构 * National Key Laboratory for Novel Software Technology, School of Computer Science, Nanjing University, P. R. China（国家新型软件技术重点实验室，计算机科学学院，南京大学） 纠错

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

Comments Accepted to NeurIPS 2025

Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

Pasin Buakhaw, Kun Kerdthaisong, Phuree Phenhiran, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot

机构 * Department of Computer Engineering and Digital Technology, Faculty of Engineering, Chulalongkorn University（朱拉隆梭大学工程学院计算机工程与数字技术系） ； Faculty of Engineering, Thammasat School of Engineering, Thammasat University（泰国 Thammasat 大学工程学院） ； Artificial Intelligence Association of Thailand（泰国人工智能协会） ； School of Biomedical Engineering & Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学学院） ； Siriraj Informatics and Data Innovation Center (SIData+), Faculty of Medicine, Siriraj Hospital, Mahidol University（玛希诺大学医学学院西里拉医院信息与数据创新中心（SIData+）） 纠错

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

Movable Antenna Enhanced Federated Fine-Tuning of Large Language Models via Hybrid Client Selection Optimization

Yang Zhao, Yue Xiu, Chengxiao Dai, Ning Wei, Dusit Niyato

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

Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection

Noshitha Padma Pratyusha Juttu, Sahithi Singireddy, Sravani Gona, Sujal Timilsina

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

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

Comments 6 pages, including figures and tables. All experiments are reproducible. Code and fine-tuned models are publicly available on: GitHub: (https://github.com/Stimils02/UnfairTOSAgreementsDetection) and Hugging Face: (https://huggingface.co/Noshitha98)

Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation

Tingjia Shen, Hao Wang, Chuan Qin, Ruijun Sun, Yang Song, Defu Lian, Hengshu Zhu, Enhong Chen

机构 * University of Science and Technology of China（中国科学技术大学） ； Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心） ； Chinese Academy of Sciences（中国科学院） ； BOSS Zhipin Career Science Lab（BOSS智联招聘科研实验室） 纠错

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

Comments 13 pages, 5 figures

ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix

Zile Yang, Ling Li, Na Di, Jinlong Pang, Yao Zhou, Hao Cheng, Bo Han, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； University of California, Santa Cruz（加州大学圣克鲁兹分校） ； Hong Kong Baptist University（香港 Baptist 大学） 纠错

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

Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion

Syed Zohaib Hassan, Pierre Lison, Pål Halvorsen

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

Comments 8 pages. Limitations, ethical considerations, and references are additional

Less is More: Local Intrinsic Dimensions of Contextual Language Models

Benjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck, Renato Vukovic, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Bastian Rieck, Marcus Zibrowius, Milica Gašić

机构 * Faculty of Mathematics and Natural Sciences, Heinrich Heine University Düsseldorf（明斯特大学数学与自然科学学院） ； Institute of AI for Health, Helmholtz Munich（健康人工智能研究所） ； Technical University of Munich（慕尼黑技术大学） ； University of Fribourg（弗里堡大学） 纠错

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

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025; in press). 10 pages, with an additional 17 pages in the appendix. Our code is available at https://github.com/aidos-lab/Topo_LLM_public and https://github.com/aidos-lab/grokking-via-lid

Journal ref Advances in Neural Information Processing Systems, Volume 38 (NeurIPS 2025)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy

Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen, Ruoming Jin, Abdallah Khreishah

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

Comments Accepted at ACML 2025 (PMLR W&CP). Code: https://github.com/kirudang/LDP_Stealing_Attack

VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon, Hyunwook Lee, Hyunmin Song, Sungahn Ko, Taehwan Kim

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

Comments EMNLP 2025. Project Website: https://vehme.github.io/

Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning

Anh Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehimwenma Nosakhare, Soundararajan Srinivasan

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

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models

Alexa R. Tartaglini, Satchel Grant, Daniel Wurgaft, Christopher Potts, Judith E. Fan

机构 * Department of Computer Science（计算机科学系） ； Department of Psychology（心理学系） ； Department of Linguistics（语言学系） ； Stanford University（斯坦福大学） 纠错

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

SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training

Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla

机构 * Critical ML, Department of Management Science and Engineering, University of Waterloo（Critical ML，管理科学与工程系，滑铁卢大学） 纠错

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

AnyECG-Lab: An Exploration Study of Fine-tuning an ECG Foundation Model to Estimate Laboratory Values from Single-Lead ECG Signals

Yujie Xiao, Gongzhen Tang, Wenhui Liu, Jun Li, Guangkun Nie, Zhuoran Kan, Deyun Zhang, Qinghao Zhao, Shenda Hong

机构 * Institute of Medical Technology, Peking University Health Science Center（北京大学人民医院医学技术研究所） ； National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院） ； School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院） ； HeartVoice Medical Technology（心声医疗技术） ； Department of Cardiology, Peking University People’s Hospital（北京大学人民医院心内科） ； Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院） ； State Key Laboratory of Vascular Homeostasis and Remodeling, NHC Key Laboratory of Cardiovascular Molecular Biology and Regulatory Peptides, Peking University（国家心血管病分子生物学与调节肽重点实验室，北京大学） 纠错

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

LLM-based Fusion of Multi-modal Features for Commercial Memorability Prediction

Aleksandar Pramov

机构 * Georgia Institute of Technology, USA（佐治亚理工学院） 纠错

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

AquaVLM: Improving Underwater Situation Awareness with Mobile Vision Language Models

Beitong Tian, Lingzhi Zhao, Bo Chen, Haozhen Zheng, Jingcheng Yang, Mingyuan Wu, Deepak Vasisht, Klara Nahrstedt

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

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

Comments 12 pages, 10 figures, under review

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Ruijie Zhang, Ziyue Liu, Zhengyang Wang, Zheng Zhang

机构 * University of California at Santa Barbara（加州大学圣芭芭拉分校） 纠错

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

ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

Jiani Huang, Amish Sethi, Matthew Kuo, Mayank Keoliya, Neelay Velingker, JungHo Jung, Ser-Nam Lim, Ziyang Li, Mayur Naik

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

Comments Accepted as a Spotlight Paper at NeurIPS 2025

Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models

Jiaxiang Liu, Jiawei Du, Xiao Liu, Prayag Tiwari, Mingkun Xu

机构 * Guangdong Institute of Intelligence Science and Technology（广东智能科学与技术研究院） ； Agency for Science, Technology and Research（科技研究局） ； School of Information Technology（信息技术学院） 纠错

专题命中 指令微调 ：language model(title,abstract)

Code Aesthetics with Agentic Reward Feedback

Bang Xiao, Lingjie Jiang, Shaohan Huang, Tengchao Lv, Yupan Huang, Xun Wu, Lei Cui, Furu Wei

机构 * Microsoft Research Asia（微软亚洲研究院） ； Zhiyuan College（智远学院） ； Shanghai Jiao Tong University（上海交通大学） ； Peking University（北京大学） 纠错

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

Comments 30 pages, 7 figures

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

Shijian Wang, Jiarui Jin, Xingjian Wang, Linxin Song, Runhao Fu, Hecheng Wang, Zongyuan Ge, Yuan Lu, Xuelian Cheng

机构 * Southeast University（东南大学） ； Monash University（墨尔本大学） ； Xiaohongshu Inc.（小红书公司） ； University of Southern California（南加州大学） ； Fudan University（复旦大学） 纠错

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

VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations

Lu Dong, Haiyu Zhang, Han Lin, Ziang Yan, Xiangyu Zeng, Hongjie Zhang, Yifei Huang, Yi Wang, Zhen-Hua Ling, Limin Wang, Yali Wang

机构 * University of Science and Technology of China（中国科学技术大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Beihang University（北京航空航天大学） ； Shanghai Jiao Tong University（上海交通大学） ； Zhejiang University（浙江大学） ； State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所） 纠错

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

Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER

Andrei Baroian

机构 * Andrei Baroian（独立研究者） 纠错

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

Comments Work done in November - December 2024

Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs

Shivam Ratnakar, Abhiroop Talasila, Raghav Chamadiya, Nikhil Agarwal, Vinayak K Doifode

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

Comments Presented at the Workshop on Preparing Good Data for Generative AI: Challenges and Approaches (Good-Data) in conjunction with AAAI 2025. The authors retain the copyright

Journal ref Workshop on Preparing Good Data for Generative AI: Challenges and Approaches, 2025

EndoSfM3D: Learning to 3D Reconstruct Any Endoscopic Surgery Scene using Self-supervised Foundation Model

Changhao Zhang, Matthew J. Clarkson, Mobarak I. Hoque

机构 * UCL Hawkes Institute（UCL哈维斯研究所） ； Department of Medical Physics（医学物理系） ； Biomedical Engineering, University College London, UK（生物医学工程，伦敦大学学院，英国） ； Division of Informatics, Imaging and Data Sciences, The University of Manchester, Manchester, UK（信息学、成像与数据科学部门，曼彻斯特大学，曼彻斯特，英国） 纠错

专题命中 指令微调 ：foundation model(title)

Comments 11 pages

A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space

Bingjie Zhang, Yibo Yang, Zhe Ren, Dandan Guo, Jindong Gu, Philip Torr, Bernard Ghanem

机构 * School of Artificial Intelligence, Jilin University（吉林大学人工智能学院） ； King Abdullah University of Science and Technology（卡塔尔国王大学科学与技术研究院） ； University of Oxford（牛津大学） 纠错

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

Agentic Reinforcement Learning for Real-World Code Repair

Siyu Zhu, Anastasiya Karpovich, Albert Chen, Jessica Koscheka, Shailesh Jannu, Di Wen, Yuqing Zhu, Rohit Jain, Alborz Geramifard

机构 * LinkedIn 纠错

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

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

Seanie Lee, Sangwoo Park, Dong Bok Lee, Dominik Wagner, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang

机构 * KAIST（韩国科学技术院） ； Technische Hochschule Nürnberg Georg Simon Ohm（图林根应用技术大学 Georg Simon Ohm 研究所） 纠错

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

Comments NeurIPS 2025