语言大模型 / LLM

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Chongli Qin, Jost Tobias Springenberg

机构 * Independent Research（独立研究者） 纠错

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

Comments See project website for details and code at: https://independentresearch.ai/posts/iwsft

Psychologically Enhanced AI Agents

Maciej Besta, Shriram Chandran, Robert Gerstenberger, Mathis Lindner, Marcin Chrapek, Sebastian Hermann Martschat, Taraneh Ghandi, Patrick Iff, Hubert Niewiadomski, Piotr Nyczyk, Jürgen Müller, Torsten Hoefler

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

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

机构 * University of Science and Technology of China（中国科学技术大学） ； Xiaohongshu Inc.（小红书公司） 纠错

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

DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding

Hengchuan Zhu, Yihuan Xu, Yichen Li, Zijie Meng, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； ZJU-Angelalign R&D Center for Intelligence Healthcare（浙江大学智能医疗研发中心） 纠错

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

Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction

Fatemeh Haji, Mazal Bethany, Cho-Yu Jason Chiang, Anthony Rios, Peyman Najafirad

机构 * Secure AI and Autonomy Lab, University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校安全人工智能与自主性实验室） ； Peraton Labs（佩拉顿实验室） ； University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校） 纠错

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

Scaling Decentralized Learning with FLock

Zehua Cheng, Rui Sun, Jiahao Sun, Yike Guo

机构 * Department of Computer Science, University of Oxford, Oxford, UK ； Newcastle University, UK ； Hong Kong University of Science ； HongKong Generative AI Research \& Development Center, Hong Kong SAR 纠错

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

Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering

Rumi Allbert, James K. Wiles, Vlad Grankovsky

机构 * Wolfram Institute（沃尔夫拉姆研究所） ； Hidoba Research（希多巴研究） 纠错

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

Riemannian Optimization for LoRA on the Stiefel Manifold

Juneyoung Park, Minjae Kang, Seongbae Lee, Haegang Lee, Seongwan Kim, Jaeho Lee

机构 * Opt-AI Inc.（Opt-AI公司） 纠错

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

Comments EMNLP 2025 Findings

DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking

Fang Wang, Tianwei Yan, Zonghao Yang, Minghao Hu, Jun Zhang, Zhunchen Luo, Xiaoying Bai

机构 * School of Computer Science, Peking University（北京大学计算机科学学院） ； School of Information Science and Engineering, Chongqing Jiaotong University（重庆交通大学信息科学与工程学院） ； China Research and Development Academy of Machinery Equipment（机械电子研究发展院） ； Center of Information Research, Academy of Military Science（军事科学信息研究中心） 纠错

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

Organ-Agents: Virtual Human Physiology Simulator via LLMs

Rihao Chang, He Jiao, Weizhi Nie, Honglin Guo, Keliang Xie, Zhenhua Wu, Lina Zhao, Yunpeng Bai, Yongtao Ma, Lanjun Wang, Yuting Su, Xi Gao, Weijie Wang, Nicu Sebe, Bruno Lepri, Bingwei Sun

机构 * Tianjin University（天津大学） ； University of Trento（特伦托大学） ； Tianjin Medical University General Hospital（天津医科大学总医院） ； Chest Hospital, Tianjin University（天津大学胸科医院） ； The Affiliated Suzhou Hospital of Nanjing Medical University（南京医科大学附属苏州医院） ； Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会） 纠错

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

Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs

Juncheng Xie, Hung-yi Lee

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

Comments 18 pages

Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation

Hassan Barmandah

机构 * Department of Software Engineering Umm Al-Qura University, Makkah, Saudi Arabia（软件工程系乌姆·阿尔·库拉大学，麦加，沙特阿拉伯） 纠错

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

Comments 7 pages, 6 figures, 2 tables. Code: https://github.com/HasanBGIt/Saudi-Dialect-ALLaM . Dataset and trained weights/adapters are not released. Primary category: cs.CL

Multidimensional classification of posts for online course discussion forum curation

Antonio Leandro Martins Candido, Jose Everardo Bessa Maia

机构 * Federal Institute of Education, Science, and Technology of Ceará (IFCE)（巴西塞阿市联邦教育、科学和技术 institute） ； State University of Ceará – CCT-PPGCC-UECE（塞阿州大学） 纠错

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

Comments 8 pages, 1 figure

CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization

Yanxia Deng, Aozhong Zhang, Selcuk Gurses, Naigang Wang, Zi Yang, Penghang Yin

机构 * Department of Mathematics and Statistics（数学与统计学系） ； University at Albany, SUNY（阿尔巴尼大学） ； IBM T. J. Watson Research Center（IBM 塔沃森研究中心） 纠错

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

Journal ref Transactions on Machine Learning Research (TMLR), 2025

Retrieval-Augmented Generation with Conflicting Evidence

Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

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

Comments COLM 2025, Data and Code: https://github.com/HanNight/RAMDocs

LLMs can be easily Confused by Instructional Distractions

Yerin Hwang, Yongil Kim, Jahyun Koo, Taegwan Kang, Hyunkyung Bae, Kyomin Jung

机构 * IPAI, Seoul National University（IPAI，首尔国立大学） ； LG AI Research（LG人工智能研究所） ； Dept. of ECE, Seoul National University（电子工程系，首尔国立大学） ； SNU-LG AI Research Center（SNU-LG人工智能研究所） 纠错

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

Comments 8 pages

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19483-19496, Vienna, Austria, July 2025

Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning

Yutong Chen, Jiandong Gao, Ji Wu

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

Comments preprint

GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction

Mohammadtaha Bagherifard, Sahar Rajabi, Ali Edalat, Yadollah Yaghoobzadeh

机构 * School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran（伊朗德黑兰大学电气与计算机工程学院） ； Tehran Institute for Advanced Studies, Khatam University, Tehran, Iran（德黑兰高级研究学院） 纠错

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

Comments Accepted to ACL 2025 (main conference, short paper), 10 pages

Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs

Jack Chen, Fazhong Liu, Naruto Liu, Yuhan Luo, Erqu Qin, Harry Zheng, Tian Dong, Haojin Zhu, Yan Meng, Xiao Wang

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

Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders

Richmond Sin Jing Xuan, Jalil Huseynov, Yang Zhang

机构 * National University of Singapore（新加坡国立大学） 纠错

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

Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs

Yushang Zhao, Huijie Shen, Dannier Li, Lu Chang, Chengrui Zhou, Yinuo Yang

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

Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process

Ermo Hua, Biqing Qi, Kaiyan Zhang, Kai Tian, Xingtai Lv, Ning Ding, Bowen Zhou

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

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

Comments Accepted to ACL 2025, Oral & Panel Discussion

Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Zhiyuan Chen, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

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

Comments Accepted by ACL 2025 Findings

Demystifying ChatGPT: How It Masters Genre Recognition

Subham Raj, Sriparna Saha, Brijraj Singh, Niranjan Pedanekar

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Patna（计算机科学与工程系，印度理工学院帕纳布分校） ； Sony Research India（索尼印度研究） 纠错

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

Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation

Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho

机构 * School of Computing Science, University of Glasgow（计算科学学院，格拉斯哥大学） 纠错

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

Comments Accepted by BioNLP@ACL 2024

Journal ref Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, ACL 2024, pp. 624-634

GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs

Sanjay Das, Swastik Bhattacharya, Souvik Kundu, Shamik Kundu, Anand Menon, Arnab Raha, Kanad Basu

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Twentieth Century Fox（二十世纪福克斯） ； Starfleet Academy（星舰学院） 纠错

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

HyperCLOVA X THINK Technical Report

NAVER Cloud HyperCLOVA X Team

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

Comments 50 pages, 13 figures; fixed figures in the appendix

SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation

Yizhe Zhang, Navdeep Jaitly

机构 * Apple（苹果公司） 纠错

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

Comments 9 pages main text

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs

Felipe Nuti, Tim Franzmeyer, João Henriques

机构 * University of Oxford（牛津大学） 纠错

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

Comments ICML 2025

Grammar and Gameplay-aligned RL for Game Description Generation with LLMs

Tsunehiko Tanaka, Edgar Simo-Serra

机构 * Waseda University（早稻田大学） 纠错

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

Comments Published at IEEE Conference on Games, 2025