语言大模型 / LLM

Omniwise: Predicting GPU Kernels Performance with LLMs

Zixian Wang, Cole Ramos, Muhammad A. Awad, Keith Lowery

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 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning

Tianyi Wu, Jingwei Ni, Bryan Hooi, Jiaheng Zhang, Elliott Ash, See-Kiong Ng, Mrinmaya Sachan, Markus Leippold

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

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Junru Zhang, Lang Feng, Xu Guo, Yuhan Wu, Yabo Dong, Duanqing Xu

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

Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems

Shang-Chi Tsai, Yun-Nung Chen

机构 * National Taiwan University（国立台湾大学） 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 IWSDS 2025 Oral Paper

Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness

Mei-Yen Chen, Thi Thu Uyen Hoang, Michael Hahn, M. Saquib Sarfraz

机构 * Saarland University（萨尔兰大学） ； Mercedes-Benz Tech Innovation（梅赛德斯-奔驰科技创新） 纠错

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

ACCORD: Autoregressive Constraint-satisfying Generation for COmbinatorial Optimization with Routing and Dynamic attention

Henrik Abgaryan, Tristan Cazenave, Ararat Harutyunyan

机构 * LAMSADE, Université Paris Dauphine-PSL（LAMSADE，巴黎Dauphine-PSL大学） 纠错

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

Slimming Down LLMs Without Losing Their Minds

Qingda, Mai

机构 * University of Waterloo（滑铁卢大学） 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 10 pages

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following

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

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学） 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 16 pages, 8 figures

Your Agent Can Defend Itself against Backdoor Attacks

Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting

机构 * Stony Brook University（石溪大学） ； Penn State University（宾夕法尼亚州立大学） 纠错

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

Text-to-LoRA: Instant Transformer Adaption

Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange

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 at ICML 2025

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Mouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun, Chenghao Liu

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 v4: accepted by ICML 2025

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs

Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao, Jen-tse Huang, Youliang Yuan, Pinjia He, Shuai Wang, Zhaopeng Tu

机构 * Renmin University of China（中国人民大学） ； Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Chinese University of Hong Kong（香港中文大学） ； Johns Hopkins University（约翰霍普金斯大学） ； Hong Kong University of Science and Technology（香港科技大学） ； Tencent（腾讯） 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 Accepted by ACL 2025

ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations

Ekaterina Grishina, Mikhail Gorbunov, Maxim Rakhuba

机构 * HSE University（俄罗斯高等经济大学） 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 ACL Findings

CleanS2S: Single-file Framework for Proactive Speech-to-Speech Interaction

Yudong Lu, Yazhe Niu, Shuai Hu, Haolin Wang

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

Taming LLMs by Scaling Learning Rates with Gradient Grouping

Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu

机构 * Zhejiang University（浙江大学） ； Westlake University（西湖大学） ； The Hong Kong University of Science and Technology（香港科技大学） ； 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.AI、cs.LG

Comments Preprint version of "Taming LLMs with Gradient Grouping" (ACL'2025). The code will be available at https://github.com/ScalingOpt/SGG

Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise

Shuai Feng, Wei-Chuang Chan, Srishti Chouhan, Junior Francisco Garcia Ayala, Srujananjali Medicherla, Kyle Clark, Mingwei Shi

机构 * Arizona State University（亚利桑那州立大学） ； National Taiwan University（台湾国立大学） ； Carnegie Mellon University（卡内基梅隆大学） ； New York University（纽约大学） ； Indian Institute of Technology Hyderabad（印度海得拉巴理工学院） ； Minitab（Minitab公司） ； Trinity College Dublin（都柏林圣三一学院） 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 14 main pages;8 page appendix

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang, Tiejun Zhao

机构 * Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院） ； Nanjing University（南京大学） ； School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院） 纠错

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

Comments Accepted to ACL2025

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data

Siwen Wang, Shitou Zhang, Wan-Lin Chen, Dung Truong, Tzyy-Ping Jung

机构 * Department of Mathematics and Computer Science, Qingdao Academy（数学与计算机科学系，青岛学院） ； Department of Information Engineering, the Chinese University of Hong Kong（信息工程系，香港中文大学） ； Department of Bioengineering, University of California, San Deigo（生物工程系，加州大学圣地亚哥分校） ； Swartz Center for Computational Neuroscience, University of California, San Diego（计算神经科学中心，加州大学圣地亚哥分校） 纠错

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

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti

机构 * University of Virginia（弗吉尼亚大学） ； University of Georgia（佐治亚大学） 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 26 pages, 13 figures

System Message Generation for User Preferences using Open-Source Models

Minbyul Jeong, Jungho Cho, Minsoo Khang, Dawoon Jung, Teakgyu Hong

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

R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen, Yuhuan Wu, Jiahao Zhao, Yingqian Min, Wayne Xin Zhao, Lei Fang, Ji-Rong Wen

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

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

Jingyu Liu, Beidi Chen, Ce Zhang

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

Comments Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition

Nam V. Nguyen, Huy Nguyen, Quang Pham, Van Nguyen, Savitha Ramasamy, Nhat Ho

机构 * FPT Software AI Center（FPT软件人工智能中心） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Institute for Infocomm Research, A ∗ STAR（信息与通信研究 institute, A ∗ STAR） 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

Comments 52 pages. This work is an improved version of the previous study at arXiv:2402.02526

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025

Sai Koneru, Maike Züfle, Thai-Binh Nguyen, Seymanur Akti, Jan Niehues, Alexander Waibel

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） 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

Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation

Mohammad Shoaib Ansari, Mohd Sohail Ali Khan, Shubham Revankar, Aditya Varma, Anil S. Mokhade

机构 * Department of Computer Science and Engineering, Visvesvaraya National Institute of Technology (VNIT), Nagpur（计算机科学与工程系，维什瓦西瓦里亚国家理工学院（VNIT），那格浦尔） 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.AI

Comments 12 pages

Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese

Silvana Yakhni, Ali Chehab

机构 * Electrical and Computer Engineering（电子与计算机工程系） ； American University of Beirut（贝鲁特美国大学） 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

Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings

Ivan Montoya Sanchez, Shaswata Mitra, Aritran Piplai, Sudip Mittal

机构 * dept. name of organization (of Aff.)（机构部门名称） 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 8 pages, 5 figures, 5 tables

In-context KV-Cache Eviction for LLMs via Attention-Gate

Zihao Zeng, Bokai Lin, Tianqi Hou, Hao Zhang, Zhijie Deng

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

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM

Shaoqing Zhang, Zhuosheng Zhang, Kehai Chen, Rongxiang Weng, Muyun Yang, Tiejun Zhao, Min Zhang

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

Comments AAAI 2025

Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions

Oded Ovadia, Meni Brief, Rachel Lemberg, Eitam Sheetrit

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