语言大模型 / LLM - arXivDaily 专题

2503.22764 2026-03-17 cs.CL cs.AI cs.LG 90%

Boosting Large Language Models with Mask Fine-Tuning

通过掩码微调提升大语言模型

Mingyuan Zhang, Yue Bai, Huan Wang, Yizhou Wang, Qihua Dong, Yitian Zhang, Yun Fu

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

AI总结本文提出掩码微调方法，通过破坏模型结构完整性提升性能，适用于多种领域和模型架构，实现平均2.70/4.15的提升。

2506.15751 2026-03-09 cs.AI cs.CL cs.LG 90%

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts

Sysformer: 通过自适应系统提示保护冻结的大语言模型

Kartik Sharma, Yiqiao Jin, Vineeth Rakesh, Yingtong Dou, Menghai Pan, Mahashweta Das, Srijan Kumar

机构 * Georgia Institute of Technology（佐治亚理工学院）； Visa Research（Visa研究）

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

AI总结 Sysformer通过自适应系统提示提高大语言模型的安全性，显著提升对有害提示的拒绝率和对安全提示的合规性。

Comments ICLR 2026. Code available at https://github.com/Ksartik/sysformer

2410.04010 2026-02-09 cs.LG cs.AI cs.CL cs.NE 90%

Hyperbolic Fine-Tuning for Large Language Models

双曲微调用于大语言模型

Menglin Yang, Ram Samarth B B, Aosong Feng, Bo Xiong, Jihong Liu, Irwin King, Rex Ying

机构 * HKUST(GZ)（香港科技大学（广州））； HKUST（香港科技大学）； Indian Institute of Science（印度科学研究院）； Yale University（耶鲁大学）； Stanford University（斯坦福大学）； The Chinese University of Hong Kong（香港中文大学）

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

AI总结 HypLoRA通过在双曲空间中进行低秩适应，提升大语言模型在算术和常识推理任务中的性能。

Comments NeurIPS 2025; https://github.com/marlin-codes/HypLoRA

2402.12819 2026-01-26 cs.CL cs.AI cs.LG 90%

Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance

比较专门化的小型模型和通用的大型模型在文本分类中的表现：100个标注样本实现平衡性能

Branislav Pecher, Ivan Srba, Maria Bielikova

机构 * Faculty of Information Technology, Brno University of Technology（信息技术学院，布拉格技术大学）； Kempelen Institute of Intelligent Technologies（智能技术研究所）

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

AI总结研究比较了专门化小型模型与通用大型模型在文本分类中的表现，发现平均100个标注样本即可实现平衡性能，且样本需求受任务特征和方差影响显著。

Comments Accepted to the EMNLP 2025 conference

2508.04748 2026-01-21 cs.LG cs.AI cs.CL 90%

AttriLens-Mol: Attribute Guided Reinforcement Learning for Molecular Property Prediction with Large Language Models

AttriLens-Mol：基于属性引导的强化学习用于利用大语言模型进行分子属性预测

Xuan Lin, Long Chen, Yile Wang

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

AI总结 AttriLens-Mol通过属性引导的强化学习框架提升大语言模型在分子属性预测中的性能，有效激发相关属性，提高可解释性和预测效果。

Comments 9 pages

2509.23773 2026-01-16 cs.LG cs.AI cs.CL cs.SI 90%

Knowledge Homophily in Large Language Models

大型语言模型中的知识同质性

Utkarsh Sahu, Zhisheng Qi, Mahantesh Halappanavar, Nedim Lipka, Ryan A. Rossi, Franck Dernoncourt, Yu Zhang, Yao Ma, Yu Wang

机构 * University of Oregon Eugene OR USA ； Pacific Northwest National Laboratory Richland WA USA ； Adobe Research San Jose CA USA ； Texas A\&M University College Station TX USA ； Rensselaer Polytechnic Institute Troy NY USA ； University of Oregon ； Pacific Northwest National Laboratory ； Adobe Research ； Texas A\&M University ； Rensselaer Polytechnic Institute

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

AI总结本文提出了一种基于图神经网络的模型，通过分析LLM知识的同质性，提高知识标注效率和推理问答性能。

2601.08141 2026-01-14 cs.CL cs.AI cs.LG 90%

Qalb: Largest State-of-the-Art Urdu Large Language Model for 230M Speakers with Systematic Continued Pre-training

Qalb：面向2.3亿使用者的最先进的乌尔都语大型语言模型，采用系统性持续预训练

Muhammad Taimoor Hassan, Jawad Ahmed, Muhammad Awais

机构 * Auburn University, USA（美国阿伯杜大学）； BHT Berlin, Germany（柏林BHT学院）； BTU Cottbus, Germany（库滕堡工业大学）

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

AI总结 Qalb通过持续预训练和监督微调，为乌尔都语构建了最先进的大型语言模型，显著提升了在多种任务上的性能。

2512.02584 2025-12-03 cs.MM 90%

Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction

分步模式引导提示框架与参数高效指令微调用于多模态事件提取

Xiang Yuan, Xinrong Chen, Haochen Li, Hang Yang, Guanyu Wang, Weiping Li, Tong Mo

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

AI总结本文提出分步模式引导提示框架与参数高效指令微调方法，用于提升多模态事件提取任务的性能。

Comments Accepted by 2025 IEEE International Conference on Multimedia and Expo

2412.15287 2025-11-27 cs.CL cs.AI cs.LG 90%

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

为大型语言模型的最佳-N采样进行推理感知微调

Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai, Sridhar Thiagarajan, Craig Boutilier, Rishabh Agarwal, Aviral Kumar, Aleksandra Faust

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

AI总结本文提出了一种推理感知微调方法，通过改进最佳-N采样策略提升大型语言模型的性能和推理效率。

2510.17895 2025-10-22 cs.LG cs.AI cs.CL 90%

Hierarchical Federated Unlearning for Large Language Models

Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu

机构 * George Mason University（乔治·玛莎大学）

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

2510.05442 2025-10-08 cs.LG cs.AI cs.CL 90%

Adversarial Reinforcement Learning for Large Language Model Agent Safety

Zizhao Wang, Dingcheng Li, Vaishakh Keshava, Phillip Wallis, Ananth Balashankar, Peter Stone, Lukas Rutishauser

机构 * Google（谷歌）； Google Deepmind（谷歌DeepMind）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Sony AI（索尼人工智能）

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

2412.05723 2025-09-29 stat.ML cs.AI cs.CL cs.LG 90%

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Haizhou Shi, Yibin Wang, Ligong Han, Huan Zhang, Hao Wang

机构 * Rutgers University（新泽西罗格斯大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Red Hat AI Innovation（红帽AI创新）

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

Comments Accepted at NeurIPS 2025

2412.00631 2025-09-01 cs.LG cs.AI cs.CL 90%

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

Yang Wu, Huayi Zhang, Yizheng Jiao, Lin Ma, Xiaozhong Liu, Jinhong Yu, Dongyu Zhang, Dezhi Yu, Wei Xu

机构 * Worcester Polytechnic Institute（沃斯特理工学院）； ByteDance Inc.（字节跳动公司）

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

Comments EMNLP 2025 Findings

2502.18793 2025-08-27 cs.SE 90%

SolEval: Benchmarking Large Language Models for Repository-level Solidity Code Generation

Zhiyuan Peng, Xin Yin, Rui Qian, Peiqin Lin, Yongkang Liu, Hao Zhang, Chenhao Ying, Yuan Luo

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

Comments Accepted By EMNLP'25-Main

2505.09805 2025-08-05 q-bio.QM cs.AI cs.CL cs.LG stat.AP 90%

Contextual Phenotyping of Pediatric Sepsis Cohort Using Large Language Models

Aditya Nagori, Ayush Gautam, Matthew O. Wiens, Vuong Nguyen, Nathan Kenya Mugisha, Jerome Kabakyenga, Niranjan Kissoon, John Mark Ansermino, Rishikesan Kamaleswaran

机构 * Department of Surgery, Duke university school of medicine（杜克大学医学学院外科部）； Department of Anesthesiology, Duke university school of medicine（杜克大学医学学院麻醉科）； Indian Institute of Technology, Goa（印度去邦理工学院）； Institute for Global Health, BC Children’s Hospital and BC Women’s Hospital + Health Centre（全球健康研究所，BC儿童医院和BC妇女医院及健康中心）； Department of Anesthesia, Pharmacology & Therapeutics, University of British Columbia（不列颠哥伦比亚大学麻醉学、药理学与治疗学系）； BC Children’s Hospital Research Institute, BC Children’s Hospital（BC儿童医院研究学院，BC儿童医院）； Department of Pediatrics, University of British Columbia（不列颠哥伦比亚大学儿科系）； Walimu, Kampala, Uganda（乌干达坎帕拉沃尔imu）； Department of Community Health, Mbarara University of Science and Technology（马巴拉拉大学科学与技术学院社区健康系）

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

Comments 11 pages, 2 Figures, 1 Table

2508.02020 2025-08-05 cs.IR 90%

Evaluating Position Bias in Large Language Model Recommendations

Ethan Bito, Yongli Ren, Estrid He

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

2501.05727 2025-08-05 cs.CL cs.AI cs.LG 90%

Self-Evolving Critique Abilities in Large Language Models

Zhengyang Tang, Ziniu Li, Zhenyang Xiao, Tian Ding, Ruoyu Sun, Benyou Wang, Dayiheng Liu, Fei Huang, Tianyu Liu, Bowen Yu, Junyang Lin

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； Shenzhen Research Institute of Big Data（深圳大数据研究院）； Shenzhen International Center for Industrial and Applied Mathematics（深圳国际工业与应用数学中心）； Qwen Team, Alibaba Inc.（阿里云通义团队）

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

Comments Accepted by COLM 2025

2404.13238 2025-06-17 cs.LG cs.AI cs.CL 90%

Personalized Wireless Federated Learning for Large Language Models

Feibo Jiang, Li Dong, Siwei Tu, Yubo Peng, Kezhi Wang, Kun Yang, Cunhua Pan, Dusit Niyato

机构 * IEEE

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

Comments 7 pages, 5 figures

2502.06854 2025-06-06 cs.LG cs.AI cs.CL 90%

Can Large Language Models Understand Intermediate Representations in Compilers?

Hailong Jiang, Jianfeng Zhu, Yao Wan, Bo Fang, Hongyu Zhang, Ruoming Jin, Qiang Guan

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

2505.20633 2025-05-28 cs.CL cs.AI cs.LG 90%

Test-Time Learning for Large Language Models

Jinwu Hu, Zhitian Zhang, Guohao Chen, Xutao Wen, Chao Shuai, Wei Luo, Bin Xiao, Yuanqing Li, Mingkui Tan

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

Comments Accepted by ICML2025

2409.08185 2025-05-22 cs.CL cs.AI cs.LG 90%

Fine-tuning Large Language Models for Entity Matching

Aaron Steiner, Ralph Peeters, Christian Bizer

机构 * University of Mannheim（曼海姆大学）

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

Comments 8 pages, 4 figures. For related code and data, see this https://github.com/wbsg-uni-mannheim/TailorMatch

2505.13515 2025-05-21 cs.LG cs.AI cs.CL 90%

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

Yanan Li, Fanxu Meng, Muhan Zhang, Shiai Zhu, Shangguang Wang, Mengwei Xu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； Peking University（北京大学）

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

2411.11389 2025-05-07 cs.CR 90%

PEEK: Phishing Evolution Framework for Phishing Generation and Evolving Pattern Analysis using Large Language Models

Fengchao Chen, Tingmin Wu, Van Nguyen, Shuo Wang, Alsharif Abuadbba, Carsten Rudolph

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

2505.00662 2025-05-02 cs.CL cs.AI cs.LG 90%

DeepCritic: Deliberate Critique with Large Language Models

Wenkai Yang, Jingwen Chen, Yankai Lin, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院）； School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）

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

Comments Work in progress. Data and models are available at https://github.com/RUCBM/DeepCritic

2404.17525 2025-05-02 cs.LG cs.AI cs.CL 90%

Large Language Model Agent as a Mechanical Designer

Yayati Jadhav, Amir Barati Farimani

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

2305.16326 2025-04-29 cs.CL cs.AI cs.IR cs.LG 90%

Benchmarking large language models for biomedical natural language processing applications and recommendations

Qingyu Chen, Yan Hu, Xueqing Peng, Qianqian Xie, Qiao Jin, Aidan Gilson, Maxwell B. Singer, Xuguang Ai, Po-Ting Lai, Zhizheng Wang, Vipina Kuttichi Keloth, Kalpana Raja, Jiming Huang, Huan He, Fongci Lin, Jingcheng Du, Rui Zhang, W. Jim Zheng, Ron A. Adelman, Zhiyong Lu, Hua Xu

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

Journal ref Nature Communications; 2025

2504.04351 2025-04-08 cs.SE cs.AI cs.CL cs.LG 90%

DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation

Jinyang Li, Sangwon Hyun, M. Ali Babar

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

Comments ICSE CAIN 2025

2410.10870 2025-04-01 cs.CL cs.AI cs.LG 90%

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

Rana Muhammad Shahroz Khan, Pingzhi Li, Sukwon Yun, Zhenyu Wang, Shahriar Nirjon, Chau-Wai Wong, Tianlong Chen

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

2503.20807 2025-03-28 stat.ML cs.AI cs.CL cs.LG 90%

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Pin-Yu Chen, Han Shen, Payel Das, Tianyi Chen

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

Comments The first two authors contribute equally to this work and are listed in alphabetical order

2503.08144 2025-03-21 cs.CV 90%

Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method

Fei Wang, Chengcheng Chen, Hongyu Chen, Yugang Chang, Weiming Zeng

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

1. 指令微调 11619 篇

Boosting Large Language Models with Mask Fine-Tuning

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts

Hyperbolic Fine-Tuning for Large Language Models

Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance

AttriLens-Mol: Attribute Guided Reinforcement Learning for Molecular Property Prediction with Large Language Models

Knowledge Homophily in Large Language Models

Qalb: Largest State-of-the-Art Urdu Large Language Model for 230M Speakers with Systematic Continued Pre-training

Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Hierarchical Federated Unlearning for Large Language Models

Adversarial Reinforcement Learning for Large Language Model Agent Safety

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

SolEval: Benchmarking Large Language Models for Repository-level Solidity Code Generation

Contextual Phenotyping of Pediatric Sepsis Cohort Using Large Language Models

Evaluating Position Bias in Large Language Model Recommendations

Self-Evolving Critique Abilities in Large Language Models

Personalized Wireless Federated Learning for Large Language Models

Can Large Language Models Understand Intermediate Representations in Compilers?

Test-Time Learning for Large Language Models

Fine-tuning Large Language Models for Entity Matching

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

PEEK: Phishing Evolution Framework for Phishing Generation and Evolving Pattern Analysis using Large Language Models

DeepCritic: Deliberate Critique with Large Language Models

Large Language Model Agent as a Mechanical Designer

Benchmarking large language models for biomedical natural language processing applications and recommendations

DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models

Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method