语言大模型 / LLM - arXivDaily 专题

2508.06754 2025-08-12 cs.AI 92%

A Fuzzy Logic Prompting Framework for Large Language Models in Adaptive and Uncertain Tasks

Vanessa Figueiredo

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

2508.07485 2025-08-12 cs.AI cs.CL cs.CY cs.LG 89%

Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

Alexander Duffy, Samuel J Paech, Ishana Shastri, Elizabeth Karpinski, Baptiste Alloui-Cros, Tyler Marques, Matthew Lyle Olson

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

2508.07860 2025-08-12 cs.CL 88%

Large Language Models for Czech Aspect-Based Sentiment Analysis

Jakub Šmíd, Pavel Přibáň, Pavel Král

机构 * University of West Bohemia in Pilsen Faculty of Applied Sciences, Department of Computer Science（西波希米亚大学应用科学学院计算机科学与工程系）

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

Comments Accepted for presentation at the 28th International Conference on Text, Speech and Dialogue (TSD 2025)

2508.06963 2025-08-12 cs.AI cs.LG 88%

MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair

Changqing Li, Tianlin Li, Xiaohan Zhang, Aishan Liu, Li Pan

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

2501.09368 2025-08-12 cs.AI 87%

Aligning Instruction Tuning with Pre-training

Yiming Liang, Tianyu Zheng, Xinrun Du, Ge Zhang, Jiaheng Liu, Xingwei Qu, Wenqiang Zu, Xingrun Xing, Chujie Zheng, Lei Ma, Guoyin Wang, Zhaoxiang Zhang, Wenhao Huang, Xiang Yue, Jiajun Zhang

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； Peking University（北京大学）

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

2508.07371 2025-08-12 cs.SE cs.AI 85%

AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation

Yi Zhong, Hongchao Liu, Di ZHao

机构 * Institute of Computing Technology（计算技术研究所）； Chinese Academy of Sciences（中国科学院）； International College（国际学院）； Beijing University of Posts and Telecommunications（北京邮电大学）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments 16pages,6figures

2508.07172 2025-08-12 cs.CL 85%

Gradient Surgery for Safe LLM Fine-Tuning

Biao Yi, Jiahao Li, Baolei Zhang, Lihai Nie, Tong Li, Tiansheng Huang, Zheli Liu

机构 * Nankai University（南开大学）

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

2508.06765 2025-08-12 cs.LG 85%

Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning

Xingke Yang, Liang Li, Sicong Li, Liwei Guan, Hao Wang, Xiaoqi Qi, Jiang Liu, Xin Fu, Miao Pan

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

2507.01216 2025-08-12 cs.LG cs.CR 85%

PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning

Xingke Yang, Liang Li, Zhiyi Wan, Sicong Li, Xiaoqi Qi, Jiang Liu, Tomoaki Ohtsuki, Xin Fu, Miao Pan

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

2404.18071 2025-08-12 cs.CL cs.LG 84%

Can Perplexity Predict Fine-tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali

Nishant Luitel, Nirajan Bekoju, Anand Kumar Sah, Subarna Shakya

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

Comments 11 pages

Journal ref Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM^2), pages 239-248, Vienna, Austria and virtual meeting, Association for Computational Linguistics, 2025

2508.02742 2025-08-12 eess.SP cs.AI cs.LG 81%

SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling

Chunyu Liu, Hao Zhang, Wei Wu, Fuhui Zhou, Qihui Wu, Derrick Wing Kwan Ng, Chan-Byoung Chae

机构 * Nanjing University of Aeronautics and Astronautics（南京航空航天大学）； Nanjing University of Posts and Telecommunications（南京邮电大学）； The University of New South Wales（新南威尔士大学）； Yonsei University（延世大学）

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

Comments This paper has been accepted for presentation at the 2025 IEEE Global Communications Conference (GLOBECOM 2025), Cognitive Radio and AI-Enabled Network Symposium

2502.04362 2025-08-12 cs.CL cs.AI 79%

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）

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

2507.17634 2025-08-12 cs.CL cs.LG 76%

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Changxin Tian, Jiapeng Wang, Qian Zhao, Kunlong Chen, Jia Liu, Ziqi Liu, Jiaxin Mao, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou

机构 * Ling Team, Ant Group（蚂蚁集团灵团队）； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高岭人工智能学院）

专题命中指令微调：LLM(title)；分类 cs.CL、cs.LG

2508.07750 2025-08-12 cs.LG cs.AI cs.CL 75%

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

Haowen Wang, Yun Yue, Zhiling Ye, Shuowen Zhang, Lei Fan, Jiaxin Liang, Jiadi Jiang, Cheng Wei, Jingyuan Deng, Xudong Han, Ji Li, Chunxiao Guo, Peng Wei, Jian Wang, Jinjie Gu

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

Comments 12 pages, 5 figures, 7 tables

2403.01422 2025-08-12 cs.CV 75%

DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes

Zhende Song, Chenchen Wang, Jiamu Sheng, Chi Zhang, Shengji Tang, Jiayuan Fan, Tao Chen

机构 * Fudan University（复旦大学）； Westlake University, Tencent PCG（西湖大学、腾讯PCG）

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

Comments Accepted by ACMM'MM 2025

2508.07577 2025-08-12 cs.CV cs.LG 74%

Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification

Zhaorui Tan, Tan Pan, Kaizhu Huang, Weimiao Yu, Kai Yao, Chen Jiang, Qiufeng Wang, Anh Nguyen, Xin Guo, Yuan Cheng, Xi Yang

机构 * Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）； Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学）； University of Liverpool（利物浦大学）； AI 3 Fudan University（复旦大学）； Duke Kunshan University（杜克-昆山大学）； BII, A ∗ STAR ； Zhejiang University（浙江大学）

专题命中指令微调：foundation model(title)；分类 cs.LG

2412.05148 2025-08-12 cs.CV cs.AI cs.LG 73%

LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation

Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli

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

Comments ICCV 2025. Project page: https://donaldssh.github.io/LoRA.rar

2508.07075 2025-08-12 cs.LG cs.AI 73%

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation

Stanley Ngugi

机构 * Stanley Ngugi（独立研究者）

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

Comments 9 pages, 2 visual aids

2508.08011 2025-08-12 cs.CL 70%

Progressive Depth Up-scaling via Optimal Transport

Mingzi Cao, Xi Wang, Nikolaos Aletras

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

2508.07466 2025-08-12 cs.AI 70%

Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs

Dom Huh, Prasant Mohapatra

机构 * UC Davis（加州大学戴维斯分校）； University of South Florida（佛罗里达州立大学）

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

2504.08780 2025-08-12 cs.IR cs.LG 70%

How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs

Atharva Nijasure, Tanya Chowdhury, James Allan

机构 * Center for Intelligent Information Retrieval, Manning College of Information and Computer Sciences, University of Massachusetts Amherst（智能信息检索中心，信息与计算机科学学院，马萨诸塞大学阿姆赫斯特分校）

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

Comments Extended Abstract

2508.06953 2025-08-12 cs.LG 70%

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Ziqiang Cui, Dugang Liu, Yuhua Li, Xiuqiang He, Ruixuan Li

机构 * Huazhong University of Science and Technology（华中科技大学）； Shenzhen Technology University（深圳技术大学）； City University of Hong Kong（香港城市大学）； Shenzhen University（深圳大学）

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

2508.07804 2025-08-12 cs.CV 67%

Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning

Bao Li, Xiaomei Zhang, Miao Xu, Zhaoxin Fan, Xiangyu Zhu, Zhen Lei

机构 * CASIA（中国科学院自动化研究所）； UCAS（中国科学院大学）； CAIR, HKISI, CAS（中国科学院自动化研究所）； Beihang University（北京航空航天大学）

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

2410.22357 2025-08-12 math.OC 67%

Zeroth-order Stochastic Cubic Newton Method Revisited

Yu Liu, Weibin Peng, Tianyu Wang, Jiajia Yu

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

2505.23870 2025-08-12 cs.LG cs.AI 62%

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection

Yixian Shen, Qi Bi, Jia-Hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania

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

Comments This work was intended as a replacement of arXiv:2410.09103 and any subsequent updates will appear there

2502.13811 2025-08-12 cs.LG cs.CL 62%

On the Duality between Gradient Transformations and Adapters

Lucas Torroba-Hennigen, Hunter Lang, Han Guo, Yoon Kim

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

Comments 17 pages, 2 figures

2410.09103 2025-08-12 cs.LG cs.AI 62%

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection

Yixian Shen, Qi Bi, Jia-Hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania

机构 * University of Amsterdam（阿姆斯特丹大学）

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

Comments 17 pages; Previously this version appeared as arXiv:2505.23870 which was submitted as a new work by accident

2508.07139 2025-08-12 cs.CR cs.AI 57%

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

Ivan Zhang

机构 * CMU（卡内基梅隆大学）

专题命中指令微调：LLM(abstract)；分类 cs.AI

Comments 10 pages, 1 figure

2505.03733 2025-08-12 cs.CL 57%

WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

Zimu Lu, Yunqiao Yang, Houxing Ren, Haotian Hou, Han Xiao, Ke Wang, Weikang Shi, Aojun Zhou, Mingjie Zhan, Hongsheng Li

机构 * Multimedia Laboratory (MMLab), The Chinese University of Hong Kong（香港中文大学多媒体实验室）

专题命中指令微调：LLM(abstract)；分类 cs.CL

2508.06880 2025-08-12 cs.CL cs.IR 57%

The ReQAP System for Question Answering over Personal Information

Philipp Christmann, Gerhard Weikum

机构 * Max Planck Institute for Informatics（马克斯·普朗克研究所信息学研究所）

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

Comments Accepted at CIKM 2025 (demonstration paper)

1. 指令微调 31 篇

A Fuzzy Logic Prompting Framework for Large Language Models in Adaptive and Uncertain Tasks

Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy

Large Language Models for Czech Aspect-Based Sentiment Analysis

MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair

Aligning Instruction Tuning with Pre-training

AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation

Gradient Surgery for Safe LLM Fine-Tuning

Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning

PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning

Can Perplexity Predict Fine-tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali

SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling

LLMs can be easily Confused by Instructional Distractions

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes

Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification

LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation

Progressive Depth Up-scaling via Optimal Transport

Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs

How Relevance Emerges: Interpreting LoRA Fine-Tuning in Reranking LLMs

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning

Zeroth-order Stochastic Cubic Newton Method Revisited

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection

On the Duality between Gradient Transformations and Adapters

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

The ReQAP System for Question Answering over Personal Information