语言大模型 / LLM - arXivDaily 专题

2503.01208 2025-06-17 cs.CV cs.CL 89%

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

Tianjie Ju, Yi Hua, Hao Fei, Zhenyu Shao, Yubin Zheng, Haodong Zhao, Mong-Li Lee, Wynne Hsu, Zhuosheng Zhang, Gongshen Liu

机构 * Shanghai Jiao Tong University（上海交通大学）； National University of Singapore（新加坡国立大学）

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

Comments Accepted at ICML 2025

2506.10047 2025-06-13 cs.CR cs.CL 89%

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models

Zilong Wang, Xiang Zheng, Xiaosen Wang, Bo Wang, Xingjun Ma, Yu-Gang Jiang

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

Comments 27 pages, 7 figures

2506.07411 2025-06-10 cs.AI 89%

An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning

Ze Yang, Yihong Jin, Juntian Liu, Xinhe Xu

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments Proceedings of 2025 IEEE 8th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE 2025)

2506.04180 2025-06-05 cs.CL 89%

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li, Roy Ka-Wei Lee

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

2506.02713 2025-06-04 cs.AI 89%

Open-Set Living Need Prediction with Large Language Models

Xiaochong Lan, Jie Feng, Yizhou Sun, Chen Gao, Jiahuan Lei, Xinlei Shi, Hengliang Luo, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系，BNRist，清华大学）

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

Comments ACL 2025 Findings

2506.01265 2025-06-03 cs.CL 89%

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines

Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong, Luu Anh Tuan, Kenji Kawaguchi, Shafiq Joty, Min-Yen Kan, Nancy F. Chen

机构 * National University of Singapore（国立新加坡大学）； Nanyang Technological University（南洋理工大学）； Institute for Infocomm Research (I 2 R)（信息通信研究院）； Salesforce AI Research（Salesforce人工智能研究）

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

Comments ACL 2025 Findings

2505.24241 2025-06-02 cs.CL 89%

Advantageous Parameter Expansion Training Makes Better Large Language Models

Naibin Gu, Yilong Chen, Zhenyu Zhang, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）； Baidu Inc.（百度公司）

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

2505.21034 2025-05-28 cs.LG cs.NE 89%

LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Wenhu Li, Niki van Stein, Thomas Bäck, Elena Raponi

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

2505.18644 2025-05-27 eess.AS cs.CL cs.SD 89%

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving

Jingran Xie, Xiang Li, Hui Wang, Yue Yu, Yang Xiang, Xixin Wu, Zhiyong Wu

机构 * Shenzhen International Graduate School（深圳国际研究生院）

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

Comments Accepted by Interspeech 2025

2406.01309 2025-05-26 cs.NE cs.AI 89%

REvolve: Reward Evolution with Large Language Models using Human Feedback

Rishi Hazra, Alkis Sygkounas, Andreas Persson, Amy Loutfi, Pedro Zuidberg Dos Martires

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

Comments Published in ICLR 2025. Project page: https://rishihazra.github.io/REvolve

2402.09546 2025-05-26 cs.RO cs.AI 89%

How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?

Congcong Wen, Jiazhao Liang, Shuaihang Yuan, Hao Huang, Geeta Chandra Raju Bethala, Yu-Shen Liu, Mengyu Wang, Anthony Tzes, Yi Fang

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

2505.16559 2025-05-23 cs.CR cs.CL 89%

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning

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

机构 * College of Cyber Science, Nankai University（南开大学网络科学学院）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）

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

2505.16107 2025-05-23 cs.CL 89%

MPL: Multiple Programming Languages with Large Language Models for Information Extraction

Bo Li, Gexiang Fang, Wei Ye, Zhenghua Xu, Jinglei Zhang, Hao Cheng, Shikun Zhang

机构 * State Key Laboratory of Intelligent Power Distribution Equipment and System（智能电力设备与系统国家重点实验室）； School of Health Sciences and Biomedical Engineering（健康科学与生物医学工程学院）； National Engineering Research Center for Software Engineering（软件工程国家工程研究中心）； Peking University（北京大学）； School of Artificial Intelligence（人工智能学院）

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

Comments Findings of ACL2025

2505.03469 2025-05-22 cs.CL 89%

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

Bin Yu, Hang Yuan, Haotian Li, Xueyin Xu, Yuliang Wei, Bailing Wang, Weizhen Qi, Kai Chen

机构 * First Author Affiliation（第一作者单位）； Second Author Affiliation（第二作者单位）

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

Comments 12 pages, 5 figures

2410.07074 2025-05-09 cs.LG 89%

Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

Zhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, Kaize Ding

机构 * Northwestern University（西北大学）； Worcester Polytechnic Institute（沃思堡理工大学）； MeiTuan（美团）

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

2505.04196 2025-05-08 cs.LG cs.MA 89%

A Large Language Model for Feasible and Diverse Population Synthesis

Sung Yoo Lim, Hyunsoo Yun, Prateek Bansal, Dong-Kyu Kim, Eui-Jin Kim

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

Comments 28 pages, 7 figures, 6 tables. Submitted to Transportation Research Part C: Emerging Technologies. Preprint version

2504.21330 2025-05-01 cs.CL 89%

Does the Prompt-based Large Language Model Recognize Students' Demographics and Introduce Bias in Essay Scoring?

Kaixun Yang, Mladen Raković, Dragan Gašević, Guanliang Chen

机构 * Centre for Learning Analytics, Monash University（学习分析中心，莫纳什大学）

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

2502.11258 2025-05-01 cs.CL 89%

Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification

Thanushon Sivakaran, En-Hui Yang

机构 * Department of Electrical and Computer Engineering University of Waterloo（电气与计算机工程系华威大学）

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

Comments 6 pages, 2 figures, Published to IEEE ISIT 2025

Journal ref 2025 IEEE International Symposium on Information Theory (ISIT 2025)

2504.16120 2025-04-24 cs.CR cs.AI 89%

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content

Chaima Njeh, Haïfa Nakouri, Fehmi Jaafar

机构 * Quebec University at Chicoutimi（魁北克大学夏斯库蒂米分校）

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

Comments This paper is under revision in the International Journal of Information Security

2502.10482 2025-04-18 cs.AI 89%

A Self-Supervised Reinforcement Learning Approach for Fine-Tuning Large Language Models Using Cross-Attention Signals

Andrew Kiruluta, Andreas Lemos, Priscilla Burity

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

2406.03230 2025-04-04 cs.CR cs.LG 89%

Defending Large Language Models Against Attacks With Residual Stream Activation Analysis

Amelia Kawasaki, Andrew Davis, Houssam Abbas

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

Comments Included in Proceedings of the Conference on Applied Machine Learning in Information Security (CAMLIS 2024), Arlington, Virginia, USA, October 24-25, 2024

2312.15960 2025-04-01 cs.LG cs.PL cs.SE 89%

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks

Jingyao Li, Pengguang Chen, Bin Xia, Hong Xu, Jiaya Jia

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

Comments Data: https://huggingface.co/datasets/JingyaoLi/MoTCode-Data,MoTCoder-32B: https://huggingface.co/JingyaoLi/MoTCoder-32B-V1.5,MoTCoder-7B: https://huggingface.co/JingyaoLi/MoTCoder-7B-v1.5,Code: https://github.com/dvlab-research/MoTCoder, Paper: arXiv:2312.15960

2503.18062 2025-03-25 cs.CL 89%

Investigating Recent Large Language Models for Vietnamese Machine Reading Comprehension

Anh Duc Nguyen, Hieu Minh Phi, Anh Viet Ngo, Long Hai Trieu, Thai Phuong Nguyen

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

2503.17578 2025-03-25 cs.LG 89%

Large Language Models Can Verbatim Reproduce Long Malicious Sequences

Sharon Lin, Krishnamurthy, Dvijotham, Jamie Hayes, Chongyang Shi, Ilia Shumailov, Shuang Song

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

2502.18008 2025-03-24 cs.SD cs.AI eess.AS 89%

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms

Yashan Wang, Shangda Wu, Jianhuai Hu, Xingjian Du, Yueqi Peng, Yongxin Huang, Shuai Fan, Xiaobing Li, Feng Yu, Maosong Sun

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

2503.16094 2025-03-21 cs.CL 89%

Cultural Alignment in Large Language Models Using Soft Prompt Tuning

Reem I. Masoud, Martin Ferianc, Philip Treleaven, Miguel Rodrigues

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

2503.13833 2025-03-19 cond-mat.mtrl-sci cs.LG 89%

Causal Discovery from Data Assisted by Large Language Models

Kamyar Barakati, Alexander Molak, Chris Nelson, Xiaohang Zhang, Ichiro Takeuchi, Sergei V. Kalinin

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

Comments 12 pages, 5 figures

2503.03135 2025-03-11 cs.LG 89%

Bridging Molecular Graphs and Large Language Models

Runze Wang, Mingqi Yang, Yanming Shen

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

Comments AAAI 2025 camera ready version

2503.04332 2025-03-07 cs.CR cs.LG 89%

The Challenge of Identifying the Origin of Black-Box Large Language Models

Ziqing Yang, Yixin Wu, Yun Shen, Wei Dai, Michael Backes, Yang Zhang

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

2407.10223 2025-03-04 cs.LG cs.CR 89%

On Large Language Model Continual Unlearning

Chongyang Gao, Lixu Wang, Kaize Ding, Chenkai Weng, Xiao Wang, Qi Zhu

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

Comments This paper has been accepted by ICLR 2025. The first two authors contribute equally and they are ordered alphabetically

1. 指令微调 11547 篇

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models

An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Open-Set Living Need Prediction with Large Language Models

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines

Advantageous Parameter Expansion Training Makes Better Large Language Models

LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving

REvolve: Reward Evolution with Large Language Models using Human Feedback

How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning

MPL: Multiple Programming Languages with Large Language Models for Information Extraction

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

A Large Language Model for Feasible and Diverse Population Synthesis

Does the Prompt-based Large Language Model Recognize Students' Demographics and Introduce Bias in Essay Scoring?

Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content

A Self-Supervised Reinforcement Learning Approach for Fine-Tuning Large Language Models Using Cross-Attention Signals

Defending Large Language Models Against Attacks With Residual Stream Activation Analysis

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks

Investigating Recent Large Language Models for Vietnamese Machine Reading Comprehension

Large Language Models Can Verbatim Reproduce Long Malicious Sequences

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms

Cultural Alignment in Large Language Models Using Soft Prompt Tuning

Causal Discovery from Data Assisted by Large Language Models

Bridging Molecular Graphs and Large Language Models

The Challenge of Identifying the Origin of Black-Box Large Language Models

On Large Language Model Continual Unlearning