语言大模型 / LLM - arXivDaily 专题

2511.22367 2025-12-01 cs.LG cs.AI cs.CL 87%

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning

SuRe: 基于惊喜的优先回放用于连续LLM学习

Hugo Hazard, Zafeirios Fountas, Martin A. Benfeghoul, Adnan Oomerjee, Jun Wang, Haitham Bou-Ammar

机构 * AI Centre, Department of Computer Science, University College London（伦敦大学学院人工智能中心、计算机科学系）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

AI总结 SuRe通过基于惊喜的优先回放和双学习者设计，提升连续LLM学习的性能和稳定性，有效缓解灾难性遗忘问题。

2511.14661 2025-11-19 cs.HC 87%

M-CALLM: Multi-level Context Aware LLM Framework for Group Interaction Prediction

Diana Romero, Xin Gao, Daniel Khalkhali, Salma Elmalaki

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

2511.10628 2025-11-17 cs.CL cs.AI cs.LG 87%

Instella: Fully Open Language Models with Stellar Performance

Jiang Liu, Jialian Wu, Xiaodong Yu, Yusheng Su, Prakamya Mishra, Gowtham Ramesh, Sudhanshu Ranjan, Chaitanya Manem, Ximeng Sun, Ze Wang, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum

机构 * AMD

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

2410.21597 2025-11-14 cs.CL cs.AI cs.LG 87%

Reducing the Scope of Language Models

David Yunis, Siyu Huo, Chulaka Gunasekara, Danish Contractor

机构 * Toyota Technological Institute at Chicago（丰田技术研究所（芝加哥））； IBM（IBM公司）

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 Appears in AAAI 2026 in the Main Technical Track

2511.08620 2025-11-13 cs.CL cs.AI cs.LG 87%

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM

Yibai Liu, Shihang Wang, Zeming Liu, Zheming Song, Junzhe Wang, Jingjing Liu, Qingjie Liu, Yunhong Wang

机构 * Fu Foundation School of Engineering and Applied Science, Columbia University（哥伦比亚大学工程与应用科学学院）； School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）

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

Comments Under review

2410.04715 2025-11-12 cs.CL cs.AI cs.LG 87%

Selection of LLM Fine-Tuning Data based on Orthogonal Rules

Xiaomin Li, Mingye Gao, Zhiwei Zhang, Chang Yue, Hong Hu

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

2511.07628 2025-11-12 stat.OT 87%

Beyond Correctness: Evaluating and Improving LLM Feedback in Statistical Education

Niklas Ippisch, Markus Herklotz, Anna-Carolina Haensch, Carsten Schwemmer

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

2510.22531 2025-10-28 cs.CL cs.AI cs.LG 87%

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）

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)

2409.17692 2025-10-17 cs.CL cs.AI cs.LG 87%

MIO: A Foundation Model on Multimodal Tokens

Zekun Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jiashuo Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

机构 * Beihang University（北航）； M-A-P ； The Hong Kong Polytechnic University（香港理工大学）； AIWaves ； University of Alberta（阿尔伯塔大学）； University of Waterloo（滑铁卢大学）； University of Manchester（曼彻斯特大学）； Chinese Academy of Sciences（中国科学院）； Peking University（北京大学）； Shanghai AI Lab（上海AI实验室）； Nanjing University（南京大学）； Kuaishou Technology（快手科技）

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

Comments EMNLP 2025 (Oral). Codes and models are available in https://github.com/MIO-Team/MIO

Journal ref EMNLP 2025

2510.00032 2025-10-02 eess.SP cs.AI cs.CL cs.LG q-bio.NC 87%

WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities

Ziyi Zeng, Zhenyang Cai, Yixi Cai, Xidong Wang, Junying Chen, Rongsheng Wang, Yipeng Liu, Siqi Cai, Benyou Wang, Zhiguo Zhang, Haizhou Li

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））

专题命中指令微调：foundation model(title)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

2509.24923 2025-09-30 cs.LG cs.AI cs.CL 87%

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

Sanxing Chen, Xiaoyin Chen, Yukun Huang, Roy Xie, Bhuwan Dhingra

机构 * Duke University（杜克大学）； Mila - Québec AI Institute（魁北克AI研究所）； Université de Montréal（蒙特利尔大学）

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

2505.07270 2025-09-25 cs.SE 87%

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation

Haoxiang Jia, Robbie Morris, He Ye, Federica Sarro, Sergey Mechtaev

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

2509.12136 2025-09-16 cs.DC 87%

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC

Tomer Bitan, Tal Kadosh, Erel Kaplan, Shira Meiri, Le Chen, Peter Morales, Niranjan Hasabnis, Gal Oren

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

Comments Accepted to IEEE HPEC conference 2025. 9 pages, incl references

2312.10032 2025-09-09 cs.CV 87%

Osprey: Pixel Understanding with Visual Instruction Tuning

Yuqian Yuan, Wentong Li, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, Jianke Zhu

机构 * Zhejiang University（浙江大学）； Ant Group（蚂蚁集团）； Microsoft（微软）； The HongKong Polytechnical University（香港理工大学）

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

Comments CVPR2024, Code and Demo link:https://github.com/CircleRadon/Osprey

2508.16100 2025-08-25 cs.CL cs.AI cs.LG 87%

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency

Zhanming Shen, Hao Chen, Yulei Tang, Shaolin Zhu, Wentao Ye, Xiaomeng Hu, Haobo Wang, Gang Chen, Junbo Zhao

机构 * Zhejiang University（浙江大学）； University of Science and Technology of China（中国科学技术大学）； Tianjin University（天津大学）

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

Comments EMNLP 2025 Main

2506.15606 2025-07-29 cs.LG cs.AI cs.CL 87%

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

Gabriel J. Perin, Runjin Chen, Xuxi Chen, Nina S. T. Hirata, Zhangyang Wang, Junyuan Hong

机构 * University of São Paulo（圣保罗大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

2507.07817 2025-07-16 cs.CL cs.AI cs.LG 87%

On the Effect of Instruction Tuning Loss on Generalization

Anwoy Chatterjee, H S V N S Kowndinya Renduchintala, Sumit Bhatia, Tanmoy Chakraborty

机构 * Dept. of Electrical Engineering（电气工程系）； Indian Institute of Technology Delhi（印度理工学院德里）； Media and Data Science Research（媒体与数据科学研究）； Adobe Inc., India（Adobe公司，印度）

专题命中指令微调：instruction tuning(title,abstract)；language model(abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments To appear in Transactions of the Association for Computational Linguistics (TACL)

2505.02579 2025-07-10 cs.CL cs.AI cs.LG 87%

EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning

Lingxiao Kong, Cong Yang, Susanne Neufang, Oya Deniz Beyan, Zeyd Boukhers

机构 * Fraunhofer Institute for Applied Information Technology（弗劳恩霍夫应用信息技术研究所）； Soochow University（苏州大学）； University Hospital of Cologne（科隆大学医院）

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

Comments 14 pages, 9 figures, accepted by the SIGDIAL 2025 conference

2506.15833 2025-06-23 cs.IR 87%

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text

Kevin Foley, Shaghayegh Agah, Kavya Priyanka Kakinada

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

Comments 7 pages, 1 figure

2504.13938 2025-06-10 cs.LG cs.AI cs.CL cs.HC 87%

Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection

Haoming Wang, Boyuan Yang, Xiangyu Yin, Wei Gao

机构 * University of Pittsburgh（匹兹堡大学）

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

Comments 15 pages

Journal ref in Proceedings of the 23rd ACM International Conference on Mobile Systems, Applications, and Services (MobiSys), 2025

2505.21109 2025-05-28 cs.CL cs.AI cs.CE cs.IR cs.LG 87%

A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction

Bogdan Bogachov, Yaoyao Fiona Zhao

机构 * McGill University, Montreal, QC, Canada（麦吉尔大学）

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

Comments 10 pages, 4 Figures, 6 Tables. This paper has been accepted to be published in the proceedings of IDETC-CIE 2025

2406.02539 2025-05-27 cs.CV cs.AI cs.CL cs.LG 87%

Parrot: Multilingual Visual Instruction Tuning

Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye

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

Comments Accepted to ICML 2025. Code and dataset are available at: https://github.com/AIDC-AI/Parrot

2505.17496 2025-05-26 cs.CL cs.AI cs.LG cs.SD eess.AS 87%

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

Chi-Yuan Hsiao, Ke-Han Lu, Kai-Wei Chang, Chih-Kai Yang, Wei-Chih Chen, Hung-yi Lee

机构 * National Taiwan University（国立台湾大学）

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

Comments Accepted to Interspeech 2025

2505.16410 2025-05-23 cs.CL cs.AI cs.LG 87%

Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning

Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, Ji-Rong Wen

机构 * Renmin University of China（中国人民大学）； BAAI（北京人工智能研究院）； Kuaishou Technology（快手科技）

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

Comments Working in progress

2503.07377 2025-05-13 cs.IR 87%

Process-Supervised LLM Recommenders via Flow-guided Tuning

Chongming Gao, Mengyao Gao, Chenxiao Fan, Shuai Yuan, Wentao Shi, Xiangnan He

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

Comments Accepted by SIGIR 2025

2504.16030 2025-04-23 cs.CV 87%

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

Joya Chen, Ziyun Zeng, Yiqi Lin, Wei Li, Zejun Ma, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室）； ByteDance（字节跳动）

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

Comments CVPR 2025. If any references are missing, please contact joyachen@u.nus.edu

2407.12879 2025-04-17 cs.CL cs.AI cs.LG 87%

Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection

Ye Jiang, Yimin Wang

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 Withdraw for new experiments

2504.10160 2025-04-15 cs.CL cs.AI cs.LG 87%

MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning

Zhaopeng Feng, Shaosheng Cao, Jiahan Ren, Jiayuan Su, Ruizhe Chen, Yan Zhang, Zhe Xu, Yao Hu, Jian Wu, Zuozhu Liu

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

Comments Work in progress. Our code is available at https://github.com/fzp0424/MT-R1-Zero

2503.24354 2025-04-10 cs.LG cs.AI cs.CL cs.CV 87%

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion

Rana Muhammad Shahroz Khan, Dongwen Tang, Pingzhi Li, Kai Wang, Tianlong Chen

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

2504.05491 2025-04-09 cs.CV 87%

REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding

Sakib Reza, Xiyun Song, Heather Yu, Zongfang Lin, Mohsen Moghaddam, Octavia Camps

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

Comments Accepted at CVPRW'25

1. 指令微调 11585 篇

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning

M-CALLM: Multi-level Context Aware LLM Framework for Group Interaction Prediction

Instella: Fully Open Language Models with Stellar Performance

Reducing the Scope of Language Models

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM

Selection of LLM Fine-Tuning Data based on Orthogonal Rules

Beyond Correctness: Evaluating and Improving LLM Feedback in Statistical Education

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

MIO: A Foundation Model on Multimodal Tokens

WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC

Osprey: Pixel Understanding with Visual Instruction Tuning

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

On the Effect of Instruction Tuning Loss on Generalization

EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text

Never Start from Scratch: Expediting On-Device LLM Personalization via Explainable Model Selection

A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction

Parrot: Multilingual Visual Instruction Tuning

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning

Process-Supervised LLM Recommenders via Flow-guided Tuning

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection

MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion

REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding