语言大模型 / LLM - arXivDaily 专题

2507.04364 2025-07-08 cs.CL cs.SI 88%

Large Language Models' Varying Accuracy in Recognizing Risk-Promoting and Health-Supporting Sentiments in Public Health Discourse: The Cases of HPV Vaccination and Heated Tobacco Products

Soojong Kim, Kwanho Kim, Hye Min Kim

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Forthcoming in Social Science & Medicine

2501.06598 2025-07-03 cs.AI 88%

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu, Maosong Sun

机构 * Tsinghua University, Beijing, China（清华大学）； Harbin Institute of Technology（哈尔滨工业大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

Comments Accepted by ACL 2025 Main, Camera Ready

2506.20269 2025-06-26 cs.CL econ.GN q-fin.EC 88%

Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models

Kai-Robin Lange, Tobias Schmidt, Matthias Reccius, Henrik Müller, Michael Roos, Carsten Jentsch

机构 * Department of Statistics, TU Dortmund University（统计系，多特蒙德大学）； Institute of Journalism, TU Dortmund University（新闻学院，多特蒙德大学）； Faculty of Management and Economics, Ruhr University Bochum（管理与经济学院，波恩大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 14 pages, 1 figure

Journal ref Proceedings of the Text2Story'25 Workshop (2025), 67-80

2506.15645 2025-06-19 cs.CV cs.AI 88%

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Shuo Xing, Lanqing Guo, Hongyuan Hua, Seoyoung Lee, Peiran Li, Yufei Wang, Zhangyang Wang, Zhengzhong Tu

机构 * Texas A&M University（德克萨斯大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of Toronto（多伦多大学）； Nanyang Technological University（南洋理工大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

Comments 18 pages

2506.15041 2025-06-19 econ.GN cs.CL q-fin.EC 88%

Identifying economic narratives in large text corpora -- An integrated approach using Large Language Models

Tobias Schmidt, Kai-Robin Lange, Matthias Reccius, Henrik Müller, Michael Roos, Carsten Jentsch

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 53 pages, 5 figures

2410.08102 2025-06-10 cs.CL 88%

Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration

Tianyi Bai, Ling Yang, Zhen Hao Wong, Fupeng Sun, Jiahui Peng, Xinlin Zhuang, Chi Zhang, Lijun Wu, Jiantao Qiu, Wentao Zhang, Binhang Yuan, Conghui He

机构 * Hong Kong University of Science and Technology（香港科技大学）； Shanghai Artificial Intelligence Laborator（上海人工智能实验室）； Peking University（北京大学）； Zhongguancun Academy（中关村学院）； Imperial College London（伦敦帝国理工学院）

专题命中预训练与数据：language model(title,abstract)；pretraining(title,abstract)；分类 cs.CL

2502.05878 2025-06-10 cs.CL 88%

Retrieval-augmented Large Language Models for Financial Time Series Forecasting

Mengxi Xiao, Zihao Jiang, Lingfei Qian, Zhengyu Chen, Yueru He, Yijing Xu, Yuecheng Jiang, Dong Li, Ruey-Ling Weng, Min Peng, Jimin Huang, Sophia Ananiadou, Qianqian Xie

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）； School of Computer Science, Wuhan University（武汉大学计算机学院）； The Fin AI（Fin AI）； Columbia University（哥伦比亚大学）； Stevens Institute of Technology（史蒂文斯理工学院）； University of Manchester（曼彻斯特大学）； University of Montreal（蒙特利尔大学）

专题命中预训练与数据：language model(title,abstract)；large language model(title)；LLM(abstract)；分类 cs.CL

Comments 11 pages, 4 figures

2506.06033 2025-06-09 cs.CL 88%

Large Language Models are Demonstration Pre-Selectors for Themselves

Jiarui Jin, Yuwei Wu, Haoxuan Li, Xiaoting He, Weinan Zhang, Yiming Yang, Yong Yu, Jun Wang, Mengyue Yang

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments ICML 2025

2406.12329 2025-06-09 cs.CL 88%

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport

Minseok Choi, Daniel Rim, Dohyun Lee, Jaegul Choo

机构 * KAIST AI（韩国科学技术院人工智能研究所）； Hyundai Motor Company（现代汽车公司）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments ACL 2025 Main

2506.02996 2025-06-04 cs.AI 88%

Linear Spatial World Models Emerge in Large Language Models

Matthieu Tehenan, Christian Bolivar Moya, Tenghai Long, Guang Lin

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

2505.23831 2025-06-02 cs.CL 88%

ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage

Wenhao Ye, Tiansheng Zheng, Yue Qi, Wenhua Zhao, Xiyu Wang, Xue Zhao, Jiacheng He, Yaya Zheng, Dongbo Wang

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 16 pages, 2 figures

2408.01063 2025-05-30 cs.CL cs.SE 88%

Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction

Quim Motger, Alessio Miaschi, Felice Dell'Orletta, Xavier Franch, Jordi Marco

机构 * Universitat Politècnica de Catalunya, Department of Service and Information System Engineering（巴塞罗那理工大学服务与信息系统工程系）； Universitat Politècnica de Catalunya, Department of Computer Science（巴塞罗那理工大学计算机科学系）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 46 pages, 7 tables, 11 figures

2505.21598 2025-05-29 cs.CL 88%

Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives

Yajiao Liu, Congliang Chen, Junchi Yang, Ruoyu Sun

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； Shenzhen Research Institute of Big Data（深圳大数据研究院）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments The first version of this paper was submitted to ACL ARR 2025 February Submission

2505.16385 2025-05-23 cs.CL 88%

Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models

Kaiyu He, Tong Zhou, Yubo Chen, Delai Qiu, Shengping Liu, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； University of Science and Technology Beijing（北京科技大学）； Unisound Al Technology Co,Ltd（Unisound人工智能技术有限公司）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 14 pages, 10 figures

2505.14126 2025-05-21 cs.LG cs.CY cs.HC cs.MA 88%

MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow

Yuan-Hao Jiang, Kezong Tang, Zi-Wei Chen, Yuang Wei, Tian-Yi Liu, Jiayi Wu

机构 * Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China（上海教育人工智能研究院，华东师范大学，上海，中国）； School of Computer Science and Technology, East China Normal University, Shanghai, China（华东师范大学计算机科学与技术学院，上海，中国）； Lab of Artificial Intelligence for Education, East China Normal University, Shanghai, China（教育人工智能实验室，华东师范大学，上海，中国）； Graduate School, Shanghai Jiao Tong University, Shanghai, China（上海交通大学研究生院，上海，中国）； School of Information Engineering, Jingdezhen Ceramic University, Jingdezhen, China（景德镇陶瓷大学信息工程学院，景德镇，中国）； School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China（江苏科技大学计算机学院，镇江，中国）； Department of Educational Information Technology, East China Normal University, Shanghai, China（教育信息技术系，华东师范大学，上海，中国）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.LG

Comments In CGI 2025: 42nd Computer Graphics International Conference, Kowloon, Hong Kong, Peper No. 134

2505.13249 2025-05-20 cs.LG 88%

RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models

Le Vu Anh, Dinh Duc Nha Nguyen, Phi Long Nguyen

机构 * TinyAI Research（TinyAI研究所）； Center for Environmental Intelligence（环境智能中心）； College of Engineering & Computer Science（工程与计算机科学学院）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.LG

Comments 12 pages, 4 figures, 3 tables

2505.10862 2025-05-19 cs.CL 88%

Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?

Tairan Fu, Miguel González, Javier Conde, Elena Merino-Gómez, Pedro Reviriego

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 6 pages, 5 figures, 2 tables

2505.08878 2025-05-15 cs.CR cs.AI cs.IT math.IT 88%

Optimized Couplings for Watermarking Large Language Models

Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun, Hsiang Hsu, Haim Permuter, Flavio P. Calmon

机构 * Ben Gurion University（本· Gurion 大学）； Harvard University（哈佛大学）； JPMorganChase（摩根大通）

专题命中预训练与数据：language model(title,abstract)；large language model(title)；LLM(abstract)；分类 cs.AI

Comments Accepted at ISIT25

2505.03501 2025-05-07 cs.CR cs.CL 88%

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

Zihan Wang, Hongwei Li, Rui Zhang, Wenbo Jiang, Kangjie Chen, Tianwei Zhang, Qingchuan Zhao, Guowen Xu

机构 * University of Electronic Science and Technology of China（电子科技大学）； Nanyang Technological University（南洋理工大学）； City University of Hong Kong（香港城市大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2505.03265 2025-05-07 cs.SE cs.AI 88%

Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models

Abdelkarim El-Hajjami, Camille Salinesi

机构 * Paris 1 Panthéon–Sorbonne University（巴黎1 Panthéon–Sorbonne大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

2504.21742 2025-05-01 cs.CL 88%

Investigating Literary Motifs in Ancient and Medieval Novels with Large Language Models

Emelie Hallenberg

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2504.16286 2025-04-29 cs.CL 88%

The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translation

Li Weigang, Pedro Carvalho Brom

机构 * Computer Science Department University of Brasilia（布拉兹利亚大学计算机科学系）； Math Department Federal Institute of Brasilia（布拉兹利亚联邦学院数学系）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 24 pages, 3 figures

2406.10602 2025-04-28 cs.CL cs.CY 88%

Multilingual Large Language Models and Curse of Multilinguality

Daniil Gurgurov, Tanja Bäumel, Tatiana Anikina

机构 * Universität des Saarlandes（萨尔兰大学）； German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2411.11260 2025-04-11 cs.CL 88%

Large corpora and large language models: a replicable method for automating grammatical annotation

Cameron Morin, Matti Marttinen Larsson

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Journal ref Linguistics Vanguard, 1-10 (2025)

2405.15232 2025-03-11 cs.CV cs.CL 88%

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception

Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 25 pages. arXiv admin note: text overlap with arXiv:2401.10208 by other authors

2502.18695 2025-02-27 cs.CY cs.AI cs.SI 88%

Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models

Konstantina Palla, José Luis Redondo García, Claudia Hauff, Francesco Fabbri, Henrik Lindström, Daniel R. Taber, Andreas Damianou, Mounia Lalmas

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

Comments 14 pages, 5 figures

2412.17395 2025-02-19 cs.CL 88%

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models

Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2408.02416 2025-02-13 cs.CL cs.CR 88%

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Haoyang Li

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Source Code: https://github.com/liangzid/PromptExtractionEval

2407.00436 2025-02-11 cs.CL 88%

A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models

Peiqin Lin, André F. T. Martins, Hinrich Schütze

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments NAACL 2025 Findings

2307.07367 2025-02-11 cs.SI cs.AI cs.CY 88%

Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow

Maria del Rio-Chanona, Nadzeya Laurentsyeva, Johannes Wachs

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

1. 预训练与数据 12403 篇

Large Language Models' Varying Accuracy in Recognizing Risk-Promoting and Health-Supporting Sentiments in Public Health Discourse: The Cases of HPV Vaccination and Heated Tobacco Products

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Identifying economic narratives in large text corpora -- An integrated approach using Large Language Models

Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration

Retrieval-augmented Large Language Models for Financial Time Series Forecasting

Large Language Models are Demonstration Pre-Selectors for Themselves

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport

Linear Spatial World Models Emerge in Large Language Models

ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage

Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction

Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives

Semantic Pivots Enable Cross-Lingual Transfer in Large Language Models

MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow

RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models

Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?

Optimized Couplings for Watermarking Large Language Models

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models

Investigating Literary Motifs in Ancient and Medieval Novels with Large Language Models

The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translation

Multilingual Large Language Models and Curse of Multilinguality

Large corpora and large language models: a replicable method for automating grammatical annotation

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception

Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models

Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow