arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 12266 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12266 篇

2411.17993 2025-09-29 cs.CL 70%

DRS: Deep Question Reformulation With Structured Output

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang

机构 * University of California, San Diego(加州大学圣地亚哥分校) University of California, Los Angelas(加州大学洛杉矶分校) The University of Queensland(昆士兰大学) National University of Singapore(新加坡国立大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments Accepted to ACL 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.09265 2025-09-29 cs.CL 70%

Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs

Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, Alexandra Birch

机构 * School of Informatics, University of Edinburgh(信息学院,爱丁堡大学) Monash University(墨尔本大学) Huawei Technologies Co., Ltd.(华为技术有限公司)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05473 2025-09-25 cs.MM cs.AI cs.SD eess.AS 70%

Embedding Alignment in Code Generation for Audio

Sam Kouteili, Hiren Madhu, George Typaldos, Mark Santolucito

机构 * Yale University(耶鲁大学) Columbia University(哥伦比亚大学)

专题命中 其他LLM :LLM(abstract);prompting(abstract);分类 cs.AI

Comments Accepted to NeurIPS 2025 AI4Music Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15139 2025-09-24 cs.CL 70%

Identifying and Answering Questions with False Assumptions: An Interpretable Approach

Zijie Wang, Eduardo Blanco

机构 * Department of Computer Science University of Arizona(计算机科学系亚利桑那大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments To appear at EMNLP 2025 Main conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20024 2025-09-23 cs.LG 70%

Using item recommendations and LLMs in marketing email titles

Deddy Jobson, Muktti Shukla, Phuong Dinh, Julio Christian Young, Nick Pittoni, Nina Chen, Ryan Ginstrom

机构 * Mercari Inc.(Mercari公司)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.LG

Comments Accepted to The Second Workshop on Generative AI for E-commerce (GenAIECommerce '25), held September 22, 2025, in Prague, Czech Republic. 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02809 2025-09-23 cs.LG math.OC stat.ML 70%

Towards Quantifying the Hessian Structure of Neural Networks

Zhaorui Dong, Yushun Zhang, Jianfeng Yao, 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 其他LLM :large language model(abstract);language model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13780 2025-09-23 cs.CL cs.CY 70%

Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions

Beatrice Savoldi, Alan Ramponi, Matteo Negri, Luisa Bentivogli

机构 * Fondazione Bruno Kessler(布鲁诺·科塞尔基金会)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15255 2025-09-22 cs.CL 70%

Comparative Analysis of Tokenization Algorithms for Low-Resource Language Dzongkha

Tandin Wangchuk, Tad Gonsalves

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments 10 Pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15253 2025-09-22 cs.SD cs.AI cs.MM eess.AS 70%

Emotion-Aware Speech Generation with Character-Specific Voices for Comics

Zhiwen Qian, Jinhua Liang, Huan Zhang

机构 * School of Electronic Engineering(电子工程学院) Computer Science Queen Mary University of London(计算机科学女王玛丽大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14936 2025-09-19 cs.LG 70%

A Comparative Analysis of Transformer Models in Social Bot Detection

Rohan Veit, Michael Lones

机构 * Department of Computer Science, Heriot-Watt University(计算机科学系,赫瑞斯学院)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.LG

Comments To appear in proceedings of UKCI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13869 2025-09-18 cs.CL 70%

Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs

Yang Liu, Chenhui Chu

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments 38 pages, 31 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10663 2025-09-18 cs.CL 70%

Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts

Zineddine Tighidet, Andrea Mogini, Hedi Ben-younes, Jiali Mei, Patrick Gallinari, Benjamin Piwowarski

机构 * BNP Paribas(BNP巴黎银行) Sorbonne Université(索邦大学) Criteo AI Lab(Criteo人工智能实验室)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments Accepted at EMNLP 2025

Journal ref EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02844 2025-09-17 cs.CV cs.CL cs.CR 70%

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection

Ziqi Miao, Yi Ding, Lijun Li, Jing Shao

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Purdue University(普渡大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments Accepted to EMNLP 2025 (Main). 17 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10922 2025-09-16 cs.CL cs.CY 70%

Aligning ESG Controversy Data with International Guidelines through Semi-Automatic Ontology Construction

Tsuyoshi Iwata, Guillaume Comte, Melissa Flores, Ryoma Kondo, Ryohei Hisano

机构 * University of Zürich (UZH)(苏黎世大学) RepRisk AG(RepRisk公司) Graduate School of Information Science and Technology, The University of Tokyo(东京大学信息科学与技术研究生院) The Canon Institute for Global Studies(佳能全球研究学院)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments Author accepted manuscript. This paper has been accepted for presentation at the ISWC 2025 Posters & Demos Track. License details will be updated once the official proceedings are published

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10216 2025-09-15 cs.NI cs.HC cs.LG 70%

RFSeek and Ye Shall Find

Noga H. Rotman, Tiago Ferreira, Hila Peleg, Mark Silberstein, Alexandra Silva

机构 * Technion - Israel Institute of Technology(技术ion-以色列理工学院) University College London(伦敦大学学院) Cornell University(康奈尔大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.LG

Comments 7 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.14699 2025-09-09 cs.SE cs.CL cs.PL 70%

Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?

Jean-Baptiste Döderlein, Nguessan Hermann Kouadio, Mathieu Acher, Djamel Eddine Khelladi, Benoit Combemale

机构 * CNRS(法国国家科学研究中心)

专题命中 其他LLM :LLM(abstract);language model(abstract);分类 cs.CL

Comments 53 pages, 3 Figures (not counted the subfigures), 16 Tables

Journal ref Journal of Systems and Software, Volume 230, December 2025, 112562

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05375 2025-09-09 cs.AI 70%

Characterizing Fitness Landscape Structures in Prompt Engineering

Arend Hintze

机构 * Department of Data Analytics, Dalarna University(数据分析系,达拉那大学) BEACON Institute for the Study of Evolution in Action, Michigan State University(进化行为研究所,密歇根州立大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05112 2025-09-08 cs.SE cs.AI 70%

GenAI-based test case generation and execution in SDV platform

Denesa Zyberaj, Lukasz Mazur, Nenad Petrovic, Pankhuri Verma, Pascal Hirmer, Dirk Slama, Xiangwei Cheng, Alois Knoll

机构 * Mercedes-Benz AG, Germany(梅赛德斯-奔驰集团,德国) Technical University of Munich, Germany(慕尼黑技术大学,德国) Ferdinand-Steinbeis-Institut der Steinbeis-Stiftung, Germany(施坦贝格基金会费尔迪南-斯坦贝格研究所,德国)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04646 2025-09-08 cs.AI cs.ET 70%

Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization

Philippe J. Giabbanelli, Ameeta Agrawal

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments Accepted at the AAAI 2025 Fall Symposium Series. November 6-8, 2025, Arlington, VA, USA

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03536 2025-09-05 cs.AI cs.HC 70%

PG-Agent: An Agent Powered by Page Graph

Weizhi Chen, Ziwei Wang, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Jiajun Bu, Yong Li, Wei Jiang

机构 * Zhejiang Key Lab of Accessible Perception \& Intelligent Systems, Zhejiang University Hangzhou China Zhejiang University

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments Paper accepted to ACM MM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17600 2025-09-05 cs.DL cs.AI cs.IR 70%

Making History Readable

Bipasha Banerjee, Jennifer Goyne, William A. Ingram

机构 * University Libraries(大学图书馆) Virginia Tech(弗吉尼亚理工学院)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.06166 2025-09-05 cs.CL 70%

Mitigating Bias in Text Classification via Prompt-Based Text Transformation

Charmaine Barker, Dimitar Kazakov

机构 * University of York(约克大学)

专题命中 其他LLM :language model(abstract);prompting(abstract);分类 cs.CL

Comments This version corrects an error in the model specification

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.06336 2025-09-04 physics.acc-ph cs.AI 70%

Towards Agentic AI on Particle Accelerators

Antonin Sulc, Thorsten Hellert, Raimund Kammering, Hayden Hoschouer, Jason St. John

机构 * Helmholtz Zentrum Berlin(柏林海德堡中心) LBNL(劳伦斯伯克利国家实验室) DESY(德意志电子同步辐射研究中心) FNAL(费米国家加速器实验室)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments 5 pages, 3 figures, Machine Learning and the Physical Sciences at Workshop at the 38th conference on Neural Information Processing Systems (NeurIPS)

Journal ref Machine Learning and the Physical Sciences Workshop at the 38th conference on Neural Information Processing Systems (NeurIPS) December 15, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01471 2025-09-03 cs.LG 70%

Hierarchical Motion Captioning Utilizing External Text Data Source

Clayton Leite, Yu Xiao

机构 * Aalto University, Espoo, Finland(艾尔沃斯大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01241 2025-09-03 cs.CV cs.AI 70%

RT-DETRv2 Explained in 8 Illustrations

Ethan Qi Yang Chua, Jen Hong Tan

机构 * Data Science and Artificial Intelligence Lab(数据科学与人工智能实验室) Singapore General Hospital(新加坡总医院)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments 5 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01147 2025-09-03 cs.CL 70%

Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective

Zhihao Zhang, Sophia Yat Mei Lee, Dong Zhang, Shoushan Li, Guodong Zhou

机构 * School of Computer Science & Technology, NLP Lab, Soochow University, China(计算机科学与技术学院、自然语言处理实验室、苏州大学) Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University(中文与双语研究系、香港理工大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

Comments EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00543 2025-09-03 cs.AI 70%

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs

Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang

机构 * Department of Civil and Environmental Engineering, University of Houston(土木与环境工程系,休斯顿大学) Center for Transportation Research, The University of Texas at Austin(交通研究中心,德克萨斯大学奥斯汀分校) Department of Information Science Technology, University of Houston(信息科学与技术系,休斯顿大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00124 2025-09-03 cs.CR cs.AI cs.CY 70%

A Whole New World: Creating a Parallel-Poisoned Web Only AI-Agents Can See

Shaked Zychlinski

机构 * JFrog

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments 10 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15825 2025-09-03 cs.CL q-fin.ST 70%

Enhancing Cryptocurrency Sentiment Analysis with Multimodal Features

Chenghao Liu, Aniket Mahanti, Ranesh Naha, Guanghao Wang, Erwann Sbai

机构 * Department of Computer Science, The University of Auckland(计算机科学系,奥克兰大学) School of Information Systems, Queensland University of Technology(信息系统学院,昆士兰技术大学) Department of Economics, The University of Auckland(经济学系,奥克兰大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02766 2025-08-27 cs.AI cs.NE cs.RO q-bio.TO 70%

Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control

Nam H. Le, Patrick Erikson, Yanbo Zhang, Michael Levin, Josh Bongard

机构 * University of Vermont(佛罗里达大学) Tufts University(塔夫茨大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);分类 cs.AI

Comments Accepted to GECCO Workshop on Bio-Inspired AI (ACM GECCO2025). 13 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏