语言大模型 / LLM - arXivDaily 专题

2410.21717 2024-10-30 cs.LG cs.AI 90%

Generating Realistic Tabular Data with Large Language Models

Dang Nguyen, Sunil Gupta, Kien Do, Thin Nguyen, Svetha Venkatesh

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

Comments To appear at ICDM 2024

2405.11724 2024-10-24 cs.CL cs.AI cs.CR cs.IR 90%

Token-wise Influential Training Data Retrieval for Large Language Models

Huawei Lin, Jikai Long, Zhaozhuo Xu, Weijie Zhao

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

Comments Accepted to ACL 2024. Keywords: Influence Function, Influence Estimation, Training Data Attribution

2410.15966 2024-10-22 cs.CL cs.AI cs.SE 90%

Self-Explained Keywords Empower Large Language Models for Code Generation

Lishui Fan, Mouxiang Chen, Zhongxin Liu

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

2310.11244 2024-10-21 cs.CL cs.LG 90%

Entity Matching using Large Language Models

Ralph Peeters, Aaron Steiner, Christian Bizer

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

Comments Published in Proceedings of the 28th International Conference on Extending Database Technology (EDBT), 25th March-28th March, 2025, ISBN 978-3-89318-098-1 on OpenProceedings.org

2410.12989 2024-10-18 cs.CL cs.AI 90%

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models

Iaroslav Chelombitko, Egor Safronov, Aleksey Komissarov

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

Comments 24 pages, 9 figures, 6 tables. Code and data available at https://github.com/nup-csai/Qtok/

2410.11550 2024-10-16 cs.AI cs.CL 90%

Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development

Tengfei Ma, Xuan Lin, Tianle Li, Chaoyi Li, Long Chen, Peng Zhou, Xibao Cai, Xinyu Yang, Daojian Zeng, Dongsheng Cao, Xiangxiang Zeng

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

Comments 12 pages, Under Review

2410.07951 2024-10-11 cs.CL cs.LG 90%

Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions

Kuleen Sasse, Shinjitha Vadlakonda, Richard E. Kennedy, John D. Osborne

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

Comments 21 pages, 3 figures, 7 tables

2406.11050 2024-10-07 cs.CL cs.AI 90%

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners

Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J. Su, Camillo J. Taylor, Dan Roth

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

Comments This paper has been accepted at EMNLP 2024

2310.00646 2024-09-26 cs.LG cs.AI stat.ML 90%

Source Attribution for Large Language Model-Generated Data

Jingtan Wang, Xinyang Lu, Zitong Zhao, Zhongxiang Dai, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low

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

2409.13935 2024-09-25 cs.CL cs.AI cs.CY 90%

MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models

Sarfaroz Yunusov, Hamza Sidat, Ali Emami

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

Comments 5 pages (excluding references), accepted to EMNLP 2024 Main Conference

2408.09895 2024-09-16 cs.CL cs.LG 90%

Performance Law of Large Language Models

Chuhan Wu, Ruiming Tang

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

Comments Personal opinions of the authors

2409.06756 2024-09-12 cs.LG cond-mat.mtrl-sci cs.AI 90%

Beyond designer's knowledge: Generating materials design hypotheses via large language models

Quanliang Liu, Maciej P. Polak, So Yeon Kim, MD Al Amin Shuvo, Hrishikesh Shridhar Deodhar, Jeongsoo Han, Dane Morgan, Hyunseok Oh

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

2404.05415 2024-09-10 cs.CL cs.AI 90%

Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations

Yiming Li, Xueqing Peng, Jianfu Li, Xu Zuo, Suyuan Peng, Donghong Pei, Cui Tao, Hua Xu, Na Hong

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

2408.16749 2024-08-30 cs.CL cs.AI 90%

Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge

Beidi Dong, Jin R. Lee, Ziwei Zhu, Balassubramanian Srinivasan

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

2405.15739 2024-08-27 cs.DL cs.AI cs.LG cs.SI 90%

Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias

Andres Algaba, Carmen Mazijn, Vincent Holst, Floriano Tori, Sylvia Wenmackers, Vincent Ginis

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

Comments 30 pages, 13 figures, 4 tables. Added GPT-4o and Claude 3.5 results

2404.04360 2024-08-08 cs.LG cs.CL cs.CR 90%

Prompt Public Large Language Models to Synthesize Data for Private On-device Applications

Shanshan Wu, Zheng Xu, Yanxiang Zhang, Yuanbo Zhang, Daniel Ramage

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

Comments COLM 2024

2407.02659 2024-08-05 cs.CL cs.LG 90%

LLMs Plagiarize: Ensuring Responsible Sourcing of Large Language Model Training Data Through Knowledge Graph Comparison

Devam Mondal, Carlo Lipizzi

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

2407.21248 2024-08-01 cs.CL cs.CR cs.LG 90%

Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens

Anqi Zhang, Chaofeng Wu

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

2407.12835 2024-07-26 cs.CL cs.AI stat.ML 90%

Regurgitative Training: The Value of Real Data in Training Large Language Models

Jinghui Zhang, Dandan Qiao, Mochen Yang, Qiang Wei

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

2407.15390 2024-07-23 cs.CL cs.AI 90%

ALLaM: Large Language Models for Arabic and English

M Saiful Bari, Yazeed Alnumay, Norah A. Alzahrani, Nouf M. Alotaibi, Hisham A. Alyahya, Sultan AlRashed, Faisal A. Mirza, Shaykhah Z. Alsubaie, Hassan A. Alahmed, Ghadah Alabduljabbar, Raghad Alkhathran, Yousef Almushayqih, Raneem Alnajim, Salman Alsubaihi, Maryam Al Mansour, Majed Alrubaian, Ali Alammari, Zaki Alawami, Abdulmohsen Al-Thubaity, Ahmed Abdelali, Jeril Kuriakose, Abdalghani Abujabal, Nora Al-Twairesh, Areeb Alowisheq, Haidar Khan

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

2310.08279 2024-06-28 cs.CL cs.AI 90%

Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement

Rui Yang, Jiahao Zhu, Jianping Man, Li Fang, Yi Zhou

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

Comments new version

2402.13414 2024-06-26 cs.LG cs.CL 90%

Harnessing Large Language Models as Post-hoc Correctors

Zhiqiang Zhong, Kuangyu Zhou, Davide Mottin

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

2406.14508 2024-06-21 cs.CL cs.AI cs.CY cs.HC 90%

Evidence of a log scaling law for political persuasion with large language models

Kobi Hackenburg, Ben M. Tappin, Paul Röttger, Scott Hale, Jonathan Bright, Helen Margetts

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

Comments 16 pages, 4 figures

2406.13163 2024-06-21 cond-mat.mtrl-sci cs.AI cs.CL 90%

LLMatDesign: Autonomous Materials Discovery with Large Language Models

Shuyi Jia, Chao Zhang, Victor Fung

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

2406.01285 2024-06-04 cs.IR cs.AI cs.LG 90%

Large Language Models as Recommender Systems: A Study of Popularity Bias

Jan Malte Lichtenberg, Alexander Buchholz, Pola Schwöbel

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

Comments Accepted at Gen-IR@SIGIR24 workshop

2405.19335 2024-05-30 cs.CV cs.CL cs.LG 90%

X-VILA: Cross-Modality Alignment for Large Language Model

Hanrong Ye, De-An Huang, Yao Lu, Zhiding Yu, Wei Ping, Andrew Tao, Jan Kautz, Song Han, Dan Xu, Pavlo Molchanov, Hongxu Yin

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

Comments Technical Report

2403.01244 2024-05-28 cs.CL cs.AI 90%

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su

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

Comments ACL 2024 main, long paper

2405.15765 2024-05-27 cs.CL cs.LG 90%

Scaling Laws for Discriminative Classification in Large Language Models

Dean Wyatte, Fatemeh Tahmasbi, Ming Li, Thomas Markovich

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

2405.07745 2024-05-14 cs.CL cs.AI 90%

LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language

Cagri Toraman

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

2403.09734 2024-05-14 cs.CL cs.AI 90%

Do Large Language Models Solve ARC Visual Analogies Like People Do?

Gustaw Opiełka, Hannes Rosenbusch, Veerle Vijverberg, Claire E. Stevenson

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

Comments Changes (based on CogSci 2024 reviewers): - Shortened Intro - Added a table summarizing children performance across age - Added Theoretical discussion in the Discussion section - Corrected the naming of plots - Small clarifications in the Methods section

1. 预训练与数据 12486 篇

Generating Realistic Tabular Data with Large Language Models

Token-wise Influential Training Data Retrieval for Large Language Models

Self-Explained Keywords Empower Large Language Models for Code Generation

Entity Matching using Large Language Models

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models

Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development

Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners

Source Attribution for Large Language Model-Generated Data

MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models

Performance Law of Large Language Models

Beyond designer's knowledge: Generating materials design hypotheses via large language models

Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations

Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge

Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias

Prompt Public Large Language Models to Synthesize Data for Private On-device Applications

LLMs Plagiarize: Ensuring Responsible Sourcing of Large Language Model Training Data Through Knowledge Graph Comparison

Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens

Regurgitative Training: The Value of Real Data in Training Large Language Models

ALLaM: Large Language Models for Arabic and English

Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement

Harnessing Large Language Models as Post-hoc Correctors

Evidence of a log scaling law for political persuasion with large language models

LLMatDesign: Autonomous Materials Discovery with Large Language Models

Large Language Models as Recommender Systems: A Study of Popularity Bias

X-VILA: Cross-Modality Alignment for Large Language Model

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

Scaling Laws for Discriminative Classification in Large Language Models

LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language

Do Large Language Models Solve ARC Visual Analogies Like People Do?