语言大模型 / LLM - arXivDaily 专题

2502.09857 2025-09-03 eess.SP 91%

Port-LLM: A Port Prediction Method for Fluid Antenna based on Large Language Models

Yali Zhang, Haifan Yin, Weidong Li, Emil Bjornson, Merouane Debbah

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

Comments 14 pages, 13 figures, 3 tables

2509.01166 2025-09-03 cs.CL cs.AI 91%

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang, Shi Wang, Shirui Pan

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空间安全学院）； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； Griffith University（格里菲斯大学）

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

Comments EMNLP 2025, Main, Long Paper

2410.01162 2025-09-03 eess.AS cs.CL cs.SD 89%

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech

Wonjune Kang, Junteng Jia, Chunyang Wu, Wei Zhou, Egor Lakomkin, Yashesh Gaur, Leda Sari, Suyoun Kim, Ke Li, Jay Mahadeokar, Ozlem Kalinli

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

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 to Interspeech 2025

2505.03238 2025-09-03 cs.RO 89%

RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning

Liam Boyle, Nicolas Baumann, Paviththiren Sivasothilingam, Michele Magno, Luca Benini

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

2501.12746 2025-09-03 cs.CL cs.AI 88%

EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering

Chang Zong, Jian Wan, Siliang Tang, Lei Zhang

机构 * Zhejiang University of Science and Technology（浙江理工大学）； Zhejiang University（浙江大学）

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

Comments 13 pages, 6 figures

2509.01341 2025-09-03 cs.CV cs.AI 88%

Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation

Yunus Serhat Bicakci, Joseph Shingleton, Anahid Basiri

机构 * Vocational School of Social Sciences, Marmara University（马尔马拉大学社会科学职业学校）； Geospatial Data Science Group, School of Geographical & Earth Sciences, University of Glasgow（格拉斯哥大学地理与地球科学学院空间数据科学小组）

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

2509.00806 2025-09-03 cs.CL cs.AI cs.LG 88%

CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA

Reem Abdel-Salam, Mary Adewunmi, Modinat A. Abayomi

机构 * Cairo University, Faculty of Engineering, Computer Engineering Department（开罗大学工程学院计算机工程系）； Menzies School of Health Research, Charles Darwin University, NT, Australia（梅恩兹健康研究学院，查尔斯达尔文大学，澳大利亚NT）； Department of Biology, Boston College, Massachusetts, USA（生物学系，波士顿学院，马萨诸塞州，美国）； Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学（RUDN大学））； Joint Institute for Nuclear Research（联合核研究中心）； Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）； University of Skövde（斯德哥尔摩大学）

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

Comments Proceedings of the BioCreative IX Challenge and Workshop (BC9): Large Language Models for Clinical and Biomedical NLP at the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, Canada, 2025

2509.01035 2025-09-03 cs.CL 87%

We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

Nikta Gohari Sadr, Sahar Heidariasl, Karine Megerdoomian, Laleh Seyyed-Kalantari, Ali Emami

机构 * Brock University（布鲁克大学）； Zoorna AI ； York University（约克大学）； Emory University（埃默里大学）

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

Comments Accepted to EMNLP 2025 Main Conference

2509.00731 2025-09-03 cs.CL 85%

LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA

Houji Jin, Negin Ashrafi, Armin Abdollahi, Wei Liu, Jian Wang, Ganyu Gui, Maryam Pishgar, Huanghao Feng

机构 * Suzhou University of Technology（苏州科技大学）； University of Southern California（南加州大学）

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

2509.00046 2025-09-03 cs.LG cs.AI 84%

Exploring and Reshaping the Weight Distribution in LLM

Chunming Ye, Songzhou Li, Xu Xu

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

Comments 19 pages,16 figures

2509.01142 2025-09-03 cs.CL 83%

Dream-Coder 7B: An Open Diffusion Language Model for Code

Zhihui Xie, Jiacheng Ye, Lin Zheng, Jiahui Gao, Jingwei Dong, Zirui Wu, Xueliang Zhao, Shansan Gong, Xin Jiang, Zhenguo Li, Lingpeng Kong

机构 * The University of Hong Kong（香港大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2503.20491 2025-09-03 cs.CV cs.CL cs.LG 82%

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

Jiale Cheng, Ruiliang Lyu, Xiaotao Gu, Xiao Liu, Jiazheng Xu, Yida Lu, Jiayan Teng, Zhuoyi Yang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang

机构 * The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University（清华大学对话人工智能（CoAI）小组）； Zhipu AI（智谱AI）； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组（KEG））

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

Comments ICCV 2025

2509.00520 2025-09-03 cs.IR cs.CL 81%

ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking

Yuzheng Cai, Yanzhao Zhang, Dingkun Long, Mingxin Li, Pengjun Xie, Weiguo Zheng

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

2504.20860 2025-09-03 cs.CV 78%

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci

机构 * University of Trento（特伦托大学）； University of Bergamo（贝拉姆奥大学）； Indian Institute of Technology Bombay（印度班加罗尔理工学院）； LNMIIT Jaipur（斋普尔LNMIIT）； The University of Queensland（昆士兰大学）； Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）

专题命中指令微调：language model(title,abstract)

Comments Accepted in ICCV 2025

2501.15144 2025-09-03 cs.CV 78%

Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models

Ankit Yadav, Lingqiao Liu, Yuankai Qi

机构 * The University of Adelaide（阿德莱德大学）； Macquarie University（麦考瑞大学）

专题命中指令微调：language model(title,abstract)

Comments 25 Pages Accepted in DICTA 2025

2509.00374 2025-09-03 cs.CV 78%

Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis

Mengke Li, Lihao Chen, Peng Zhang, Yiu-ming Cheung, Hui Huang

机构 * College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室）； National Laboratory of Radar Signal Processing, Xidian University（雷达信号处理国家实验室）； Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）

专题命中指令微调：foundation model(title,abstract)

2509.01312 2025-09-03 cs.CL 77%

TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering

Sishi Xiong, Ziyang He, Zhongjiang He, Yu Zhao, Changzai Pan, Jie Zhang, Zhenhe Wu, Shuangyong Song, Yongxiang Li

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

2502.11419 2025-09-03 cs.CL 77%

InsBank: Evolving Instruction Subset for Ongoing Alignment

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

机构 * School of Computer Science, Beijing Institute of Technology（计算机科学学院，北京理工大学）

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

2509.02550 2025-09-03 cs.CL 70%

PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture

Fakhraddin Alwajih, Abdellah El Mekki, Hamdy Mubarak, Majd Hawasly, Abubakr Mohamed, Muhammad Abdul-Mageed

机构 * The University of British Columbia（不列颠哥伦比亚大学）； Qatar Computing Research Institute（卡塔尔计算研究所）

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

Comments https://palmx.dlnlp.ai/

2509.00421 2025-09-03 cs.LG 70%

Memory Limitations of Prompt Tuning in Transformers

Maxime Meyer, Mario Michelessa, Caroline Chaux, Vincent Y. F. Tan

机构 * Department of Mathematics, National University of Singapore（新加坡国立大学数学系）； IPAL, IRL2955, Singapore（新加坡IPAL）； School of Computing, National University of Singapore（新加坡国立大学计算机学院）； Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系）

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

2507.09509 2025-09-03 cs.CL 70%

How Important is `Perfect' English for Machine Translation Prompts?

Patrícia Schmidtová, Niyati Bafna, Seth Aycock, Gianluca Vico, Wiktor Kamzela, Katharina Hämmerl, Vilém Zouhar

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

2506.14589 2025-09-03 cs.RO 67%

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving

Ren Xin, Hongji Liu, Xiaodong Mei, Wenru Liu, Maosheng Ye, Zhili Chen, Jun Ma

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）

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

Comments This work has been submitted to the IEEE for possible publication

2509.00820 2025-09-03 cs.CR 67%

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models

Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han

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

Comments Accepted By EMNLP2025

2509.00527 2025-09-03 cs.CV 50%

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement

Ruitao Wu, Yifan Zhao, Jia Li

机构 * State Key Laboratory of Virtual Reality Technology and Systems, SCSE & QRI, Beihang University（虚拟现实技术与系统国家重点实验室，北京航空航天大学）

专题命中指令微调：language model(abstract)

Comments Accepted by ICCV 2025

2509.00305 2025-09-03 cs.CV 50%

Language-Aware Information Maximization for Transductive Few-Shot CLIP

Ghassen Baklouti, Maxime Zanella, Ismail Ben Ayed

机构 * École de Technologie Supérieure (ÉTS)（École de Technologie Supérieure）； Université Catholique de Louvain (UCLouvain)（Université Catholique de Louvain）； Université de Mons (UMons)（Université de Mons）

专题命中指令微调：language model(abstract)

2503.16055 2025-09-03 eess.IV cs.CV 50%

SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank Transformation

Abdelrahman Elsayed, Sarim Hashmi, Mohammed Elseiagy, Hu Wang, Mohammad Yaqub, Ibrahim Almakky

机构 * Mohamed Bin Zayed University of Artificial Intelligence（Mohamed Bin Zayed人工智能大学）

专题命中指令微调：foundation model(abstract)

Comments BMVC 2025

1. 指令微调 26 篇

Port-LLM: A Port Prediction Method for Fluid Antenna based on Large Language Models

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech

RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning

EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering

Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation

CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA

We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA

Exploring and Reshaping the Weight Distribution in LLM

Dream-Coder 7B: An Open Diffusion Language Model for Code

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization

ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models

Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis

TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering

InsBank: Evolving Instruction Subset for Ongoing Alignment

PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture

Memory Limitations of Prompt Tuning in Transformers

How Important is `Perfect' English for Machine Translation Prompts?

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement

Language-Aware Information Maximization for Transductive Few-Shot CLIP

SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank Transformation