语言大模型 / LLM - arXivDaily 专题

2509.10641 2025-11-07 cs.LG cs.AI 90%

Test-Time Warmup for Multimodal Large Language Models

Nikita Rajaneesh, Thomas Zollo, Richard Zemel

机构 * Columbia University（哥伦比亚大学）

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

2502.00706 2025-10-31 cs.CR cs.CL cs.LG 90%

Model Provenance Testing for Large Language Models

Ivica Nikolic, Teodora Baluta, Prateek Saxena

机构 * National University of Singapore（新加坡国立大学）； Georgia Institute of Technology（佐治亚理工学院）

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.LG

2308.08728 2025-10-23 cs.AI cs.CL 90%

Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing

Zhe Zheng, Jin Han, Ke-Yin Chen, Xin-Yu Cao, Xin-Zheng Lu, Jia-Rui Lin

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

Journal ref Engineering Applications of Artificial Intelligence, 2026

2510.10248 2025-10-20 cs.LG cs.AI 90%

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Jiaxi Zhuang, Yaorui Shi, Jue Hou, Yunong He, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Ying Qian, Linfeng Zhang, Guolin Ke, Hengxing Cai

机构 * DP Technology（DP技术公司）； Shanghai Jiao Tong University（上海交通大学）； East China Normal University（华东师范大学）

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

2509.03937 2025-10-14 cs.CL cs.AI 90%

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning

Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han

机构 * Harbin Institute of Technology（哈尔滨工业大学）； Pengcheng Laboratory（鹏城实验室）

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

Comments EMNLP 2025 Findings

2510.01606 2025-10-03 cs.IR cs.AI cs.CL 90%

Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations

Bo Ma, LuYao Liu, Simon Lau, Chandler Yuan, and XueY Cui, Rosie Zhang

机构 * Department of Software \& Microelectronics, Peking University, Beijing, China ； Economic Law School, China University of Political Science ； Financial Media, Peking University, ChangSha, China

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

2509.24866 2025-10-02 cs.CL cs.AI 90%

Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning

Matteo Fuoli, Weihang Huang, Jeannette Littlemore, Sarah Turner, Ellen Wilding

机构 * Department of Linguistics and Communication（语言学与传播学系）； University of Birmingham（伯明翰大学）； Centre for Arts, Memory & Communities（艺术、记忆与社区中心）； Coventry University（考文垂大学）

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

2509.26584 2025-10-01 cs.AI cs.IR cs.LG cs.SE 90%

Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models

Matheus Vinicius da Silva de Oliveira, Jonathan de Andrade Silva, Awdren de Lima Fontao

机构 * Faculty of Computing - Federal University of Mato Grosso do Sul（计算机学院 - 短暂戈亚那联邦大学）

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

2411.11027 2025-10-01 cs.CL cs.AI 90%

BianCang: A Traditional Chinese Medicine Large Language Model

Sibo Wei, Xueping Peng, Yi-Fei Wang, Tao Shen, Jiasheng Si, Weiyu Zhang, Fa Zhu, Athanasios V. Vasilakos, Wenpeng Lu, Xiaoming Wu, Yinglong Wang

机构 * Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), and with Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（计算机功率网络与信息安全重点实验室，教育部，山东计算机科学中心（国家超级计算机中心济南中心），齐鲁工业大学（山东科学院），并与山东省计算功率互联网与服务计算省级重点实验室，山东省计算机科学基础研究中心）； Australian Artificial Intelligence Institute, University of Technology Sydney（澳大利亚人工智能研究所，技术悉尼大学）； Affiliated Hospital of Shandong University of Traditional Chinese Medicine（山东中医药大学附属医院）； College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University（信息科学与技术及人工智能学院，南京林业大学）； Department of ICT and Center for AI Research, University of Agder (UiA)（ICT系和人工智能研究中心，阿格德大学（UiA））

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

Journal ref IEEE Journal of Biomedical and Health Informatics (Early Access), 2025, 1-12

2410.11020 2025-09-29 cs.CL cs.AI 90%

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning

Bokai Hu, Sai Ashish Somayajula, Xin Pan, Pengtao Xie

机构 * UC San Diego（加州大学圣地亚哥分校）

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

2509.16244 2025-09-23 quant-ph cs.CL cs.LG 90%

How Can Quantum Deep Learning Improve Large Language Models?

Emily Jimin Roh, Hyojun Ahn, Samuel Yen-Chi Chen, Soohyun Park, Joongheon Kim

机构 * Korea University（韩国大学）； Wells Fargo（摩根大通）； Sookmyung Women's University（-sookmyung女子大学）

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

2509.12937 2025-09-17 cs.CR cs.AI cs.CL 90%

Jailbreaking Large Language Models Through Content Concretization

Johan Wahréus, Ahmed Hussain, Panos Papadimitratos

机构 * Networked Systems Security (NSS) Group（网络系统安全组）； KTH Royal Institute of Technology（皇家理工学院）

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

Comments Accepted for presentation in the Conference on Game Theory and AI for Security (GameSec) 2025

2509.12110 2025-09-16 eess.SP cs.CL cs.LG 90%

When marine radar target detection meets pretrained large language models

Qiying Hu, Linping Zhang, Xueqian Wang, Gang Li, Yu Liu, Xiao-Ping Zhang

机构 * Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学）； State Key Laboratory of Space Network and Communications, Tsinghua University（空间网络与通信国家重点实验室，清华大学）； Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School, Tsinghua University（深圳 ubiquitous 数据赋能重点实验室，清华大学深圳国际研究生院）

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

2509.04512 2025-09-08 cs.CL cs.LG 90%

Scaling behavior of large language models in emotional safety classification across sizes and tasks

Edoardo Pinzuti, Oliver Tüscher, André Ferreira Castro

机构 * Leibniz Institute for Resilience Research（莱比锡韧性研究所）； University Medical Center Halle（哈雷医学院）； German Center for Mental Health (DZPG)（德国心理健康中心（DZPG））； University Medical Center of the Johannes Gutenberg-University Mainz（美因茨约瑟夫·冯·拉贝大学医学院）

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

2509.03527 2025-09-05 cs.CL cs.AI 90%

Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model

Bohdan M. Pavlyshenko

机构 * Ivan Franko National University of Lviv（弗拉基米尔·伊万诺维奇·帕瓦利申科国立大学）

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

2508.18739 2025-08-27 cs.CL cs.LG 90%

Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models

Chang Wang, Siyu Yan, Depeng Yuan, Yuqi Chen, Yanhua Huang, Yuanhang Zheng, Shuhao Li, Yinqi Zhang, Kedi Chen, Mingrui Zhu, Ruiwen Xu

机构 * Xiaohongshu Inc.（小红书公司）； East China Normal University（东华大学）

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

2502.09183 2025-08-22 cs.CL cs.AI 90%

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation

Changzhi Zhou, Xinyu Zhang, Dandan Song, Xiancai Chen, Wanli Gu, Huipeng Ma, Yuhang Tian, Mengdi Zhang, Linmei Hu

机构 * School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China（北京理工大学计算机科学与技术学院）； Peking University（北京大学）； 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.CL、cs.AI

2506.04385 2025-08-15 cs.CL cs.AI 90%

MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP

Kurt Micallef, Claudia Borg

机构 * Department of Artificial Intelligence, University of Malta（人工智能系，马耳他大学）

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

Comments mT5 XXL & EuroLLM Instruct 9B 1-shot results

2504.09753 2025-08-01 cs.CL cs.AI 90%

Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance

Ram Mohan Rao Kadiyala, Siddartha Pullakhandam, Siddhant Gupta, Drishti Sharma, Jebish Purbey, Kanwal Mehreen, Muhammad Arham, Suman Debnath, Hamza Farooq

机构 * Vantager ； Cohere for AI Community ； IIT Roorkee（印度理工学院罗尔基）； Amazon（亚马逊）； Stanford University（斯坦福大学）

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

Comments 24 pages, 18 figures

2411.08003 2025-07-31 cs.AI cs.CL cs.CY cs.FL 90%

Can adversarial attacks by large language models be attributed?

Manuel Cebrian, Andres Abeliuk, Jan Arne Telle

机构 * Center for Automation and Robotics, Spanish National Research Council（自动化与机器人中心，西班牙国家研究理事会）； Department of Computer Science, University of Chile（计算机科学系，智利大学）； Department of Informatics, University of Bergen（信息学系，卑尔根大学）

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

Comments 22 pages, 5 figures, 2 tables

2507.18523 2025-07-25 cs.CL cs.CY cs.HC cs.LG 90%

The Moral Gap of Large Language Models

Maciej Skorski, Alina Landowska

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

Comments preprint

2507.11502 2025-07-16 cs.CL cs.CE cs.LG 90%

HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong

Sirui Han, Junqi Zhu, Ruiyuan Zhang, Yike Guo

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

2501.10487 2025-07-10 cs.CL cs.AI 90%

Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data

TaeYoon Kwack, Jisoo Kim, Ki Yong Jung, DongGeon Lee, Heesun Park

机构 * Sungkyunkwan University（成均馆大学）； Pohang University of Science and Technology（釜山科学技术大学）

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

Comments Accepted to TRL@ACL 2025

2503.00030 2025-07-09 cs.LG cs.AI 90%

RSPO: Regularized Self-Play Alignment of Large Language Models

Xiaohang Tang, Sangwoong Yoon, Seongho Son, Huizhuo Yuan, Quanquan Gu, Ilija Bogunovic

机构 * University College London（伦敦大学学院）； University of California, Los Angeles（加州大学洛杉矶分校）

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

Comments Preprint

2502.05638 2025-07-09 cs.CL cs.AI 90%

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports

Aynur Guluzade, Naguib Heiba, Zeyd Boukhers, Florim Hamiti, Jahid Hasan Polash, Yehya Mohamad, Carlos A Velasco

机构 * Fraunhofer Institute for Applied Information Technology（弗劳恩霍夫应用信息科技研究所）

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

2507.05065 2025-07-08 cs.LG cs.AI 90%

Replacing thinking with tool usage enables reasoning in small language models

Corrado Rainone, Tim Bakker, Roland Memisevic

机构 * Qualcomm AI Research（高通人工智能研究）

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

Comments 23 pages, includes appendix

2408.14774 2025-07-08 cs.LG cs.CL 90%

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora

专题命中指令微调：LLM(title,abstract)；instruction tuning(title)；SFT(abstract)；prompting(abstract)

Journal ref International Conference on Learning Representations (ICLR 2025)

2505.11010 2025-07-08 cs.CL cs.AI 90%

ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models

Jiangxu Wu, Cong Wang, TianHuang Su, Jun Yang, Haozhi Lin, Chao Zhang, Ming Peng, Kai Shi, SongPan Yang, BinQing Pan, ZiXian Li, Ni Yang, ZhenYu Yang

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

Comments ACL2025 Accepted

2506.12576 2025-07-01 cs.CL cs.AI 90%

Enabling Precise Topic Alignment in Large Language Models Via Sparse Autoencoders

Ananya Joshi, Celia Cintas, Skyler Speakman

机构 * Carnegie Mellon University（卡内基梅隆大学）； IBM Research（IBM研究院）

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

2506.09428 2025-07-01 cs.CL cs.AI 90%

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting

Fei Ding, Baiqiao Wang

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

1. 指令微调 11619 篇

Test-Time Warmup for Multimodal Large Language Models

Model Provenance Testing for Large Language Models

Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning

Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations

Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning

Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models

BianCang: A Traditional Chinese Medicine Large Language Model

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning

How Can Quantum Deep Learning Improve Large Language Models?

Jailbreaking Large Language Models Through Content Concretization

When marine radar target detection meets pretrained large language models

Scaling behavior of large language models in emotional safety classification across sizes and tasks

Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model

Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation

MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP

Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance

Can adversarial attacks by large language models be attributed?

The Moral Gap of Large Language Models

HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong

Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data

RSPO: Regularized Self-Play Alignment of Large Language Models

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports

Replacing thinking with tool usage enables reasoning in small language models

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models

Enabling Precise Topic Alignment in Large Language Models Via Sparse Autoencoders

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting