语言大模型 / LLM

Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation

Yang Wu, Yifan Zhang, Yurong Wu, Yuran Wang, Junkai Zhang, Jian Cheng

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

Comments 17 pages, 12 figures

StoryWriter: A Multi-Agent Framework for Long Story Generation

Haotian Xia, Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li

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

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Zhiyuan Liang, Dongwen Tang, Yuhao Zhou, Xuanlei Zhao, Mingjia Shi, Wangbo Zhao, Zekai Li, Peihao Wang, Konstantin Schürholt, Damian Borth, Michael M. Bronstein, Yang You, Zhangyang Wang, Kai Wang

机构 * National University of Singapore（新加坡国立大学） ； UT Austin（德克萨斯大学奥斯汀分校） ； University of St. Gallen（圣加尔登大学） ； Oxford University（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、cs.LG

Comments We propose a method that can generate LoRA parameters in seconds

DeepRTL2: A Versatile Model for RTL-Related Tasks

Yi Liu, Hongji Zhang, Yunhao Zhou, Zhengyuan Shi, Changran Xu, Qiang Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； National Technology Innovation Center for EDA（EDA国家技术创新中心） 纠错

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

Comments ACL 2025 Findings

Convergent Linear Representations of Emergent Misalignment

Anna Soligo, Edward Turner, Senthooran Rajamanoharan, Neel Nanda

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

Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning

Ziyu Zhao, Yixiao Zhou, Zhi Zhang, Didi Zhu, Tao Shen, Zexi Li, Jinluan Yang, Xuwu Wang, Jing Su, Kun Kuang, Zhongyu Wei, Fei Wu, Yu Cheng

机构 * Zhejiang University（浙江大学） ； Shanghai Innovation Institute（上海创新研究院） ； ByteDance Inc.（字节跳动公司） ； Fudan University（复旦大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Jie Xie, Wei Zhou, Wang Xu, Yuanheng Zhang, Zhou Su, Zhongwu Zhai, Xiaoming Liu, Yudong Mei, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

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

Comments Updated results in Table 2 and Table 3; The project is available at https://github.com/OpenBMB/AgentCPM-GUI

Model Organisms for Emergent Misalignment

Edward Turner, Anna Soligo, Mia Taylor, Senthooran Rajamanoharan, Neel Nanda

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

FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems

Val Andrei Fajardo, David B. Emerson, Amandeep Singh, Veronica Chatrath, Marcelo Lotif, Ravi Theja, Alex Cheung, Izuki Matsuba

机构 * Vector Institute（向量研究所） 纠错

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

Comments 9 pages, 4 figures, 2 tables. Accepted for the CODEML Workshop at ICML 2025. Framework code available at https://github.com/VectorInstitute/fed-rag

Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Data

Hao Xiong, Chuanyuan Tan, Wenliang Chen

机构 * School of Computer Science and Technology, Soochow University（计算机科学与技术学院，苏州大学） 纠错

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

CTDGSI: A comprehensive exploitation of instance selection methods for automatic text classification. VII Concurso de Teses, Dissertações e Trabalhos de Graduação em SI -- XXI Simpósio Brasileiro de Sistemas de Informação

Washington Cunha, Leonardo Rocha, Marcos André Gonçalves

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

Comments 16 pages, 5 figures, 2 tables

MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding

Weikang Qiu, Zheng Huang, Haoyu Hu, Aosong Feng, Yujun Yan, Rex Ying

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

Comments Forty-Second International Conference on Machine Learning (ICML 2025)

Refining Adaptive Zeroth-Order Optimization at Ease

Yao Shu, Qixin Zhang, Kun He, Zhongxiang Dai

机构 * Yao Shu ； Qixin Zhang ； Kun He ； Zhongxiang Dai 纠错

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

Comments Published as a conference paper at ICML 2025

Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs

Aleksey Kudelya, Alexander Shirnin

机构 * HSE University（俄罗斯高等经济大学） 纠错

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

Comments Accepted to SemEval-2025, an ACL 2025 workshop

IMPersona: Evaluating Individual Level LM Impersonation

Quan Shi, Carlos E. Jimenez, Stephen Dong, Brian Seo, Caden Yao, Adam Kelch, Karthik Narasimhan

机构 * Princeton Language and Intelligence (PLI)（普林斯顿语言与智能中心） 纠错

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

Comments 25 pages, 9 pages main

Soft Measures for Extracting Causal Collective Intelligence

Maryam Berijanian, Spencer Dork, Kuldeep Singh, Michael Riley Millikan, Ashlin Riggs, Aadarsh Swaminathan, Sarah L. Gibbs, Scott E. Friedman, Nathan Brugnone

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

Comments Camera-ready version accepted for publication in the EMNLP 2024 Workshop NLP4Science

R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning

Jinda Liu, Yi Chang, Yuan Wu

机构 * School of Artificial Intelligence, Jilin University（吉林大学人工智能学院） ； Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国） ； International Center of Future Science, Jilin University（未来科学国际中心，吉林大学） 纠错

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

Comments 8 pages, 7 figures

Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection

Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda

机构 * Department of Electrical Engineering, Yale University（耶鲁大学电气工程系） ； Intel Labs（英特尔实验室） 纠错

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

Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning

Runtao Ren, Jian Ma, Jianxi Luo

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

Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach

Dongyue Li, Ziniu Zhang, Lu Wang, Hongyang R. Zhang

机构 * Northeastern University, Boston, MA（东北大学） ； University of Michigan, Ann Arbor, MI（密歇根大学） 纠错

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

Comments 17 pages. Appeared in Findings of EMNLP'24

Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment

Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James T. Kwok

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Southern University of Science and Technology（南方科技大学） 纠错

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

SparQLe: Speech Queries to Text Translation Through LLMs

Amirbek Djanibekov, Hanan Aldarmaki

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

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

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

Haoran Luo, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, Luu Anh Tuan

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

Comments Accepted by ICML 2025 main conference

Journal ref ICML 2025

Rethinking the Understanding Ability across LLMs through Mutual Information

Shaojie Wang, Sirui Ding, Na Zou

机构 * Department of Industrial and Systems Engineering（工业与系统工程系） ； University of Houston（休斯敦大学） ； Bakar Computational Health Sciences Institute（巴卡计算健康科学研究所） ； UCSF 纠错

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

MAP: Revisiting Weight Decomposition for Low-Rank Adaptation

Chongjie Si, Zhiyi Shi, Yadao Wang, Xiaokang Yang, Susanto Rahardja, Wei Shen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Harvard University（哈佛大学） ； Alibaba Group（阿里巴巴集团） ； Singapore Institute of Technology（新加坡科技学院） 纠错

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

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Zihong Chen, Wanli Jiang, Jinzhe Li, Zhonghang Yuan, Huanjun Kong, Wanli Ouyang, Nanqing Dong

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Temporal Sampling for Forgotten Reasoning in LLMs

Yuetai Li, Zhangchen Xu, Fengqing Jiang, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Xiang Yue, Radha Poovendran

机构 * University of Washington（华盛顿大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Western Washington University（西华盛顿大学） 纠错

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

Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages

Gulfarogh Azam, Mohd Sadique, Saif Ali, Mohammad Nadeem, Erik Cambria, Shahab Saquib Sohail, Mohammad Sultan Alam

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

Origin Tracer: A Method for Detecting LoRA Fine-Tuning Origins in LLMs

Hongyu Liang, Yuting Zheng, Yihan Li, Yiran Zhang, Shiyu Liang

机构 * Shanghai Jiao Tong University（上海交通大学） ； National University of Defense Technology（国防科技大学） 纠错

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

GiFT: Gibbs Fine-Tuning for Code Generation

Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen

机构 * Nanyang Technological University（南洋理工大学） 纠错

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

Comments Accepted to ACL 2025