语言大模型 / LLM - arXivDaily 专题

2505.17615 2025-05-26 cs.LG cs.CL cs.IR 88%

Large language model as user daily behavior data generator: balancing population diversity and individual personality

Haoxin Li, Jingtao Ding, Jiahui Gong, Yong Li

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

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

Comments 14 pages, 7 figures, 4 tables

2505.14892 2025-05-22 cs.CL cs.AI 88%

Scaling Laws for State Dynamics in Large Language Models

Jacob X Li, Shreyas S Raman, Jessica Wan, Fahad Samman, Jazlyn Lin

机构 * Brown University（布朗大学）

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

Comments 16 pages; 23 figures

2405.17067 2025-05-16 cs.CL cs.AI 88%

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization

Dixuan Wang, Yanda Li, Junyuan Jiang, Zepeng Ding, Ziqin Luo, Guochao Jiang, Jiaqing Liang, Deqing Yang

机构 * School of Data Science, Fudan University（复旦大学数据科学学院）； School of Management, Fudan University（复旦大学管理学院）

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

2504.21214 2025-05-06 cs.CL cs.AI eess.AS 88%

Pretraining Large Brain Language Model for Active BCI: Silent Speech

Jinzhao Zhou, Zehong Cao, Yiqun Duan, Connor Barkley, Daniel Leong, Xiaowei Jiang, Quoc-Toan Nguyen, Ziyi Zhao, Thomas Do, Yu-Cheng Chang, Sheng-Fu Liang, Chin-teng Lin

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

2504.12459 2025-04-18 cs.CL cs.AI 88%

On Linear Representations and Pretraining Data Frequency in Language Models

Jack Merullo, Noah A. Smith, Sarah Wiegreffe, Yanai Elazar

机构 * Brown University（布朗大学）； Allen Institute for AI (Ai2)（艾伦人工智能研究所）； University of Washington（华盛顿大学）

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

Comments ICLR 2025

2412.11302 2025-04-17 cs.CL cs.LG 88%

Sequence-Level Leakage Risk of Training Data in Large Language Models

Trishita Tiwari, G. Edward Suh

机构 * Cornell University（康奈尔大学）； Nvidia（英伟达公司）

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

2504.10900 2025-04-16 cs.LG cs.AI 88%

Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization

Peiliang Gong, Emadeldeen Eldele, Min Wu, Zhenghua Chen, Xiaoli Li, Daoqiang Zhang

专题命中预训练与数据：foundation model(title,abstract)；pretraining(title,abstract)；分类 cs.AI、cs.LG

2504.07854 2025-04-11 cs.CL cs.AI 88%

The KL3M Data Project: Copyright-Clean Training Resources for Large Language Models

Michael J Bommarito, Jillian Bommarito, Daniel Martin Katz

机构 * Institute for the Advancement of Legal and Ethical AI (ALEA Institute)（法律与伦理AI推进研究所（ALEA研究所））； CodeX—The Stanford Center for Legal Informatics（CodeX——斯坦福法律信息学中心）； Illinois Tech—Chicago Kent College of Law（伊利诺伊理工大学芝加哥肯特法学院）； Center for Legal Technology & Data Science, Bucerius Law School（布塞留斯法学院法律技术与数据科学中心）

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

Comments 27 pages, 7 figures, 9 table

2406.12725 2025-04-03 cs.CL cs.AI 88%

Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction

Atharva Naik, Kexun Zhang, Nathaniel Robinson, Aravind Mysore, Clayton Marr, Hong Sng, Rebecca Byrnes, Anna Cai, Kalvin Chang, David Mortensen

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

2406.07155 2025-03-18 cs.AI cs.CL cs.MA cs.NI cs.SI 88%

Scaling Large Language Model-based Multi-Agent Collaboration

Chen Qian, Zihao Xie, YiFei Wang, Wei Liu, Kunlun Zhu, Hanchen Xia, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun

机构 * Tsinghua University（清华大学）； Peng Cheng Laboratory（鹏城实验室）

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

Comments Accepted to ICLR-2025

2503.04930 2025-03-10 cs.CL cs.AI 88%

HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models

Yao Ge, Yuting Guo, Sudeshna Das, Swati Rajwal, Selen Bozkurt, Abeed Sarker

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

2503.02141 2025-03-05 cs.LG cs.CL cs.CR 88%

Network Traffic Classification Using Machine Learning, Transformer, and Large Language Models

Ahmad Antari, Yazan Abo-Aisheh, Jehad Shamasneh, Huthaifa I. Ashqar

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

2503.01151 2025-03-04 cs.CL cs.AI cs.IR 88%

ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

Feng Wang, Zesheng Shi, Bo Wang, Nan Wang, Han Xiao

机构 * Jina AI GmbH（吉纳人工智能有限公司）

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

Comments 9 pages, 10-12 refs

2503.00449 2025-03-04 cs.CL cs.AI 88%

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models

Yanyue Zhang, Yulan He, Deyu Zhou

机构 * The Alan Turing Institute（阿兰·图灵研究所）

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

Comments 17 pages, 3 figures

2503.00084 2025-03-04 cs.SD cs.AI cs.CL eess.AS 88%

InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation

Chong Zhang, Yukun Ma, Qian Chen, Wen Wang, Shengkui Zhao, Zexu Pan, Hao Wang, Chongjia Ni, Trung Hieu Nguyen, Kun Zhou, Yidi Jiang, Chaohong Tan, Zhifu Gao, Zhihao Du, Bin Ma

机构 * Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室）

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

Comments Work in progress. Correspondence regarding this technical report should be directed to {chong.zhang, yukun.ma}@alibaba-inc.com. Online demo available on https://modelscope.cn/studios/iic/InspireMusic and https://huggingface.co/spaces/FunAudioLLM/InspireMusic

2502.18505 2025-02-27 cs.SE cs.AI cs.CL 88%

Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models

Ranjan Sapkota, Shaina Raza, Manoj Karkee

机构 * Cornell University（康奈尔大学）； Vector Institute（向量研究所）； Washington State University（华盛顿州立大学）

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

2404.05893 2025-02-24 cs.AI cs.CL cs.IR 88%

Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models

Sowmya S. Sundaram, Benjamin Solomon, Avani Khatri, Anisha Laumas, Purvesh Khatri, Mark A. Musen

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

2409.02370 2025-02-17 cs.CL cs.AI 88%

Do Large Language Models Possess Sensitive to Sentiment?

Yang Liu, Xichou Zhu, Zhou Shen, Yi Liu, Min Li, Yujun Chen, Benzi John, Zhenzhen Ma, Tao Hu, Zhi Li, Zhiyang Xu, Wei Luo, Junhui Wang

机构 * ByteDance（字节跳动）

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

Comments 10 pages, 2 figures

2407.08441 2025-02-14 cs.CL cs.AI 88%

Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation

Riccardo Cantini, Giada Cosenza, Alessio Orsino, Domenico Talia

机构 * University of Calabria（卡拉布里亚大学）

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

2404.02936 2025-02-13 cs.CL cs.LG 88%

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Jingyang Zhang, Jingwei Sun, Eric Yeats, Yang Ouyang, Martin Kuo, Jianyi Zhang, Hao Frank Yang, Hai Li

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

Comments ICLR'25 Spotlight. Project page and code is available at https://zjysteven.github.io/mink-plus-plus/

2502.05248 2025-02-11 cs.CL cs.AI cs.MA 88%

Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires

Pranav Bhandari, Usman Naseem, Amitava Datta, Nicolas Fay, Mehwish Nasim

机构 * School of Physics, Mathematics and Computing（物理、数学与计算学院）； University of Western Australia（西澳大学）； School of Computing（计算机学院）； School of Psychological Sciences（心理科学学院）

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

Comments Accepted for publication at TheWebConf 2025

2406.06663 2025-02-10 cs.CR cs.CL cs.LG 88%

SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection

Sakshi Mahendru, Tejul Pandit

机构 * Palo Alto Networks（帕洛阿尔托网络公司）

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

Comments Preprint. 10 pages, Accepted in IEEE 7th International Conference on Big Data and Artificial Intelligence (BDAI 2024)

Journal ref 2024 IEEE 7th International Conference on Big Data and Artificial Intelligence (BDAI), Beijing, China, 2024, pp. 160-169

2502.03429 2025-02-06 cs.CL cs.AI 88%

On Fairness of Unified Multimodal Large Language Model for Image Generation

Ming Liu, Hao Chen, Jindong Wang, Liwen Wang, Bhiksha Raj Ramakrishnan, Wensheng Zhang

机构 * Iowa State University（爱荷华州立大学）； Carnegie Mellon University（卡内基梅隆大学）； William Mary University（威廉玛丽大学）

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

2501.13720 2025-02-04 cs.CL cs.AI cs.SD eess.AS 88%

Musical ethnocentrism in Large Language Models

Anna Kruspe

机构 * Munich University of Applied Sciences（慕尼黑应用科学大学）

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

Journal ref Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA) 2024

2411.15287 2025-01-30 cs.CL cs.AI 88%

Sycophancy in Large Language Models: Causes and Mitigations

Lars Malmqvist

机构 * The Tech Collective（科技联合体）

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

Journal ref Computing Conference 2025 (upcoming)

2501.16247 2025-01-28 cs.LG cs.CL 88%

Zero-Shot Decision Tree Construction via Large Language Models

Lucas Carrasco, Felipe Urrutia, Andrés Abeliuk

机构 * University of Chile（智利大学）； National Center for Artificial Intelligence (CENIA)（国家人工智能中心（CENIA））

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

2501.14818 2025-01-28 cs.CV cs.AI cs.LG 88%

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

Zhiqi Li, Guo Chen, Shilong Liu, Shihao Wang, Vibashan VS, Yishen Ji, Shiyi Lan, Hao Zhang, Yilin Zhao, Subhashree Radhakrishnan, Nadine Chang, Karan Sapra, Amala Sanjay Deshmukh, Tuomas Rintamaki, Matthieu Le, Ilia Karmanov, Lukas Voegtle, Philipp Fischer, De-An Huang, Timo Roman, Tong Lu, Jose M. Alvarez, Bryan Catanzaro, Jan Kautz, Andrew Tao, Guilin Liu, Zhiding Yu

专题命中预训练与数据：language model(title,abstract)；post-training(title,abstract)；分类 cs.AI、cs.LG

2501.11747 2025-01-27 cs.CL cs.AI 88%

Optimizing Pretraining Data Mixtures with LLM-Estimated Utility

William Held, Bhargavi Paranjape, Punit Singh Koura, Mike Lewis, Frank Zhang, Todor Mihaylov

机构 * Meta AI ； Stanford University（斯坦福大学）； Georgia Institute of Technology（佐治亚理工学院）

专题命中预训练与数据：LLM(title)；pretraining(title)；large language model(abstract)；language model(abstract)

Comments 10 pages, 8 figures

2412.14670 2024-12-20 cs.CL cs.AI 88%

Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT

Hassane Kissane, Achim Schilling, Patrick Krauss

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

2412.07144 2024-12-16 cs.AI cs.CL 88%

Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models

Hao Li, Ruoyuan Gong, Hao Jiang

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

Comments Accepted at AAAI 2025

1. 预训练与数据 12486 篇

Large language model as user daily behavior data generator: balancing population diversity and individual personality

Scaling Laws for State Dynamics in Large Language Models

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization

Pretraining Large Brain Language Model for Active BCI: Silent Speech

On Linear Representations and Pretraining Data Frequency in Language Models

Sequence-Level Leakage Risk of Training Data in Large Language Models

Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization

The KL3M Data Project: Copyright-Clean Training Resources for Large Language Models

Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction

Scaling Large Language Model-based Multi-Agent Collaboration

HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models

Network Traffic Classification Using Machine Learning, Transformer, and Large Language Models

ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models

InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation

Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models

Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models

Do Large Language Models Possess Sensitive to Sentiment?

Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires

SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection

On Fairness of Unified Multimodal Large Language Model for Image Generation

Musical ethnocentrism in Large Language Models

Sycophancy in Large Language Models: Causes and Mitigations

Zero-Shot Decision Tree Construction via Large Language Models

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

Optimizing Pretraining Data Mixtures with LLM-Estimated Utility

Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT

Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models