语言大模型 / LLM

Metadata Conditioned Large Language Models for Localization

具有元数据条件的大型语言模型用于本地化

Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos

机构 * Department of Computer Science, George Mason University（计算机科学系，乔治·马歇尔大学） 纠错

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

AI总结 本文提出通过元数据条件来提升大型语言模型的本地化能力，通过预训练和实验验证了其在不同区域表现的提升效果和效率优势。

Comments under review

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection

DNF：用于大语言模型知识产权保护的双层嵌套指纹

Zhenhua Xu, Yiran Zhao, Mengting Zhong, Dezhang Kong, Changting Lin, Tong Qiao, Meng Han

机构 * Zhejiang University（浙江大学） ； Binjiang Institute of Zhejiang University（浙江大学滨江学院） ； Hangzhou Dianzi University（杭州电子科技大学） ； Hefei University of Technology（合肥工业大学） 纠错

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

AI总结 DNF通过结合领域特定风格线索和隐含语义触发器，实现大语言模型的隐蔽知识产权保护。

Comments Accepted by ICASSP2026

Differentially Private Subspace Fine-Tuning for Large Language Models

针对大语言模型的差分隐私子空间微调

Lele Zheng, Xiang Wang, Tao Zhang, Yang Cao, Ke Cheng, Yulong Shen

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

AI总结 DP-SFT通过子空间微调方法在保持差分隐私保障的同时，有效降低噪声影响，提升大语言模型在下游任务中的准确性和稳定性。

Exploring the Translation Mechanism of Large Language Models

探索大型语言模型的翻译机制

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Xiucheng Li, Yang Xiang, Min Zhang

机构 * Institute of Computing and Intelligence（计算与智能研究所） ； Harbin Institute of Technology（哈尔滨工业大学） ； Peng Cheng Laboratory（鹏城实验室） 纠错

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

AI总结 本研究提出子空间干预路径修补法，揭示大型语言模型翻译机制，发现稀疏组件子集主导翻译，通过微调提升性能并推广至复杂任务。

Comments Accepted in NeurIPS 2025 Poster

EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning

EDCO：面向领域特定大语言模型微调的动态课程编排

Jing-Cheng Pang, Liu Sun, Chang Zhou, Xian Tang, Haichuan Ma, Kun Jiang, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai, Chenwei Wu, Xubin Li, Xin Chen

机构 * Huawei Technologies Co., Ltd（华为技术有限公司） 纠错

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

AI总结 EDCO通过动态课程编排和熵估计提升领域特定大语言模型微调效率与准确性。

Hybrid and Unitary PEFT for Resource-Efficient Large Language Models

混合与单位元PEFT用于资源高效的大型语言模型

Haomin Qi, Zihan Dai, Chengbo Huang

机构 * Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong（信息工程系，香港中文大学） ； Department of Electrical and Computer Engineering, University of California San Diego, USA（电气与计算机工程系，加州大学圣地亚哥分校） ； Department of Computer Science, University of Copenhagen, Denmark（计算机科学系，哥本哈根大学） ； Department of Electrical Engineering, Columbia University, USA（电气工程系，哥伦比亚大学） 纠错

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

AI总结 本文提出混合与单位元PEFT方法，通过结合BOFT和LoRA-GA的优势，提升LLM微调效率，减少训练时间和内存使用，适用于资源受限场景。

Comments 11 pages, 2 figures and 7 table

Journal ref American Journal of Computer Science and Technology (Volume 8, Issue 4, 2025)

Scaling Reinforcement Learning for Content Moderation with Large Language Models

利用大语言模型扩展强化学习用于内容审核

Hamed Firooz, Rui Liu, Yuchen Lu, Zhenyu Hou, Fangzhou Xiong, Xiaoyang Zhang, Changshu Jian, Zhicheng Zhu, Jiayuan Ma, Jacob Tao, Chaitali Gupta, Xiaochang Peng, Shike Mei, Hang Cui, Yang Qin, Shuo Tang, Jason Gaedtke, Arpit Mittal

机构 * Meta AI 纠错

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

AI总结 本文提出利用强化学习扩展大语言模型，以提升内容审核的准确性和效率，特别是在标签稀疏和政策复杂的情况下。

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions

通过对比安全与有害分布实现大语言模型的安全对齐

Xiaoyun Zhang, Zhengyue Zhao, Wenxuan Shi, Kaidi Xu, Di Huang, Xing Hu

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

AI总结 本文提出ACD方法，通过生成安全与对抗性提示，实现大语言模型的安全对齐，提升安全性的同时保持生成能力。

Integrating Ontologies with Large Language Models for Enhanced Control Systems in Chemical Engineering

将本体与大语言模型结合以增强化工工程中的控制系统

Crystal Su, Kuai Yu, Jingrui Zhang, Mingyuan Shao, Daniel Bauer

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

AI总结 本文提出结合本体的LLM框架，用于增强化工工程控制系统，通过结构化知识与生成推理结合，提升过程控制和安全分析的可解释性和可靠性。

Comments This paper is withdrawn due to issues with attribution and citation accuracy

Large Language Model based Smart Contract Auditing with LLMBugScanner

基于大型语言模型的智能合约审计与LLMBugScanner

Yining Yuan, Yifei Wang, Yichang Xu, Zachary Yahn, Sihao Hu, Ling Liu

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

AI总结 LLMBugScanner通过结合领域知识适应和集成推理，提升智能合约漏洞检测的鲁棒性和泛化能力，提供了一种高效且可扩展的审计框架。

Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models

Daniyal Ganiuly, Assel Smaiyl

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

Comments 10 pages, 6 figures

Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being

Kathleen W. Guan, Sarthak Giri, Mohammed Amara, Bernard J. Jansen, Enrico Liscio, Milena Esherick, Mohammed Al Owayyed, Ausrine Ratkute, Gayane Sedrakyan, Mark de Reuver, Joao Fernando Ferreira Goncalves, Caroline A. Figueroa

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

Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models

Mohammed N. Swileh, Shengli Zhang

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

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Amir Hossein Rahmati, Sanket Jantre, Weifeng Zhang, Yucheng Wang, Byung-Jun Yoon, Nathan M. Urban, Xiaoning Qian

机构 * Texas A&M University（德克萨斯A&M大学） ； Brookhaven National Laboratory（布鲁克海文国家实验室） 纠错

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

Comments Conference on Neural Information Processing Systems (NeurIPS 2025)

From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization

Suswitha Pericharla, Daniel B. Hier, Tayo Obafemi-Ajayi

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

Comments Submitted for publication to BMC BioData Mining

ParaVul: A Parallel Large Language Model and Retrieval-Augmented Framework for Smart Contract Vulnerability Detection

Tenghui Huang, Jinbo Wen, Jiawen Kang, Siyong Chen, Zhengtao Li, Tao Zhang, Dongning Liu, Jiacheng Wang, Chengjun Cai, Yinqiu Liu, Dusit Niyato

机构 * School of Automation, Guangdong University of Technology（广东科技大學自動化學院） ； College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大學計算機科學與技術學院） ； School of Cyberspace Science and Technology, Beijing Jiaotong University（北京交通大學網絡空間科學與技術學院） ； School of Computer Science and Technology, Guangdong University of Technology（廣東科技大學計算機科學與技術學院） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大學計算與數據科學學院） 纠错

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

Yet Another Watermark for Large Language Models

Siyuan Bao, Ying Shi, Zhiguang Yang, Hanzhou Wu, Xinpeng Zhang

机构 * School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院） ； School of Big Data and Computer Science, Guizhou Normal University（贵州师范大学大数据与计算机科学学院） 纠错

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

Comments https://scholar.google.com/citations?hl=en&user=IdiF7M0AAAAJ

Journal ref International Conference on Communications and Broadband Networking (2025)

DSCD: Large Language Model Detoxification with Self-Constrained Decoding

Ming Dong, Jinkui Zhang, Bolong Zheng, Xinhui Tu, Po Hu, Tingting He

机构 * Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning（湖北人工智能与智能学习省级重点实验室） ； National Language Resources Monitoring and Research Center for Network Media（网络媒体语言资源监测与研究国家中心） ； Central China Normal University（中央财经大学） ； Wuhan University of Technology（武汉理工大学） 纠错

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 at EMNLP 2025 MainConference

JAI-1: A Thai-Centric Large Language Model

Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Pontakorn Trakuekul, Sumana Sumanakul, Natchanon Pollertlam

机构 * Jasmine Technology Solution, Thailand ； Department of Linguistics, Chulalongkorn University, Thailand（语言学系，朱拉隆功大学） 纠错

专题命中 指令微调 ：language model(title,abstract)；large language model(title)；LLM(abstract)；post-training(abstract)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services

Yansong Li, Zhixing Tan, Paula Branco, Yang Liu

机构 * University of Ottawa（渥太华大学） ； Zhongguancun Laboratory（中关村实验室） ； School of Electrical Engineering and Computer Science（电气工程与计算机科学学院） ； Department of Computer Science and Technology（计算机科学与技术系） ； Institute for AI Industry Research (AIR)（人工智能产业研究院） 纠错

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

Journal ref IEEE Transactions on Audio, Speech, and Language Processing 33 (2025) 4085-4097

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning

Hang Hua, Yolo Yunlong Tang, Chenliang Xu, Jiebo Luo

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

Comments Accepted to AAAI 2025

Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation

Reza Fayyazi, Rozhina Taghdimi, Shanchieh Jay Yang

机构 * Department of Electrical & Computer Engineering（电气与计算机工程系） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

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

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning

Yolo Yunlong Tang, Jinrui Zhang, Xiangchen Wang, Teng Wang, Feng Zheng

机构 * SUSTech VIP Lab（四川大学VIP实验室） 纠错

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

Comments Winner solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2023 workshop)

A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis

Ziheng Geng, Jiachen Liu, Ran Cao, Lu Cheng, Haifeng Wang, Minghui Cheng

机构 * Department of Civil and Architectural Engineering, University of Miami（迈阿密大学土木与建筑工程系） ； Department of Electrical and Computer Engineering, University of Miami（迈阿密大学电气与计算机工程系） ； College of Civil Engineering, Hunan University（湖南大学土木学院） ； Department of Computer Science, University of Illinois Chicago（伊利诺伊大学芝加哥分校计算机科学系） ； Department of Civil and Environmental Engineering, Washington State University（华盛顿州立大学土木与环境工程系） ； School of Architecture, University of Miami（迈阿密大学建筑学院） 纠错

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

Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge

Yuan Huang

机构 * Shenzhen College of International Education（深圳国际教育学院） 纠错

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

A critical review of methods and challenges in large language models

Milad Moradi, Ke Yan, David Colwell, Matthias Samwald, Rhona Asgari

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

DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns

Ranfei Chen, Ming Chen

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（智能信息处理重点实验室，计算技术研究所，中国科学院，北京，中国） ； Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（计算机网络信息中心，中国科学院，北京，中国） 纠错

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

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter

Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Singapore Management University（新加坡管理大学） ； Central South University（中南大学） ； iFLYTEK AI Research (Central China), iFLYTEK Co., Ltd（iFLYTEK中央中国研究院，iFLYTEK公司） 纠错

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

Comments 21 pages, 9 figures, 17 tables

Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction

Sumanta Bhattacharyya, Sara Riazi, Pedram Rooshenas

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

DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models

Honghui Xu, Shiva Shrestha, Wei Chen, Zhiyuan Li, Zhipeng Cai

机构 * Department of Information Technology, Kennesaw State University（信息科技系，肯纳邦大学） ； Department of Computer Science, Georgia State University（计算机科学系，佐治亚州立大学） 纠错

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