语言大模型 / LLM - arXivDaily 专题

2503.05828 2025-03-11 cs.AI econ.TH 70%

Market-based Architectures in RL and Beyond

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

机构 * University of Warwick（华威大学）

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

Comments Accepted at AAMAS 2025

2502.18878 2025-03-07 cs.CL 70%

Learning to Generate Structured Output with Schema Reinforcement Learning

Yaxi Lu, Haolun Li, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Zhiyuan Liu, Fangming Liu, Maosong Sun

机构 * Tsinghua University（清华大学）； Renmin University of China（中国人民大学）； Peng Cheng Laboratory（鹏城实验室）

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

Comments 8 pages, 4 figures

2501.08600 2025-03-05 cs.SE cs.AI 70%

AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL

Tyler Stennett, Myeongsoo Kim, Saurabh Sinha, Alessandro Orso

机构 * Georgia Institute of Technology（佐治亚理工学院）； IBM Research（IBM研究院）

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

Comments To be published in the 47th IEEE/ACM International Conference on Software Engineering - Demonstration Track (ICSE-Demo 2025)

2410.05472 2025-03-05 cs.CL 70%

Neural machine translation system for Lezgian, Russian and Azerbaijani languages

Alidar Asvarov, Andrey Grabovoy

机构 * Antiplagiat（反剽窃公司）； Dagestan State University（达吉斯坦国立大学）； Moscow Institue of Physics and Technology（莫斯科物理技术学院）

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

2503.01063 2025-03-04 cs.CL 70%

AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding

David Noever

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

2503.00821 2025-03-04 astro-ph.IM cs.AI 70%

AI Agents for Ground-Based Gamma Astronomy

D. Kostunin, V. Sotnikov, S. Golovachev, A. Strube

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

Comments proceedings of ADASS2025 (submitted), original talk and demos: https://pretalx.com/adass2024/talk/TRFZKU/

2502.20429 2025-03-04 cs.SE cs.AI 70%

Will AI replace Software Engineers? Do not hold your breath

Abhik Roychoudhury, Andreas Zeller

机构 * National University of Singapore（新加坡国立大学）； CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）

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

Comments 3 pages

2502.12361 2025-03-04 cs.CL 70%

ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining

Xiao Yu, Ruize Xu, Chengyuan Xue, Jinzhong Zhang, Xu Ma, Zhou Yu

机构 * Columbia University（哥伦比亚大学）； University of Toronto（多伦多大学）； Intellipro Group Inc.（英泰利普罗集团公司）

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

Comments arXiv admin note: text overlap with arXiv:2401.16349

2408.08291 2025-03-04 cs.CL 70%

The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community

Shachar Don-Yehiya, Leshem Choshen, Omri Abend

机构 * The Hebrew University of Jerusalem（耶路撒冷希伯来大学）； MIT（麻省理工学院）； MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）

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

2502.20834 2025-03-03 cs.CL 70%

Learning to Substitute Components for Compositional Generalization

Zhaoyi Li, Gangwei Jiang, Chenwang Wu, Ying Wei, Defu Lian, Enhong Chen

机构 * School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）； Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机科学系）； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）

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

Comments 23 pages, 9 figures, preprint, the extension paper of the paper (arXiv:2306.02840)

2502.20757 2025-03-03 cs.CL 70%

The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents

Yihong Tang, Kehai Chen, Xuefeng Bai, Zhengyu Niu, Bo Wang, Jie Liu, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology（哈尔滨工业大学计算与智能学院）； Baidu Inc.（百度公司）； College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）

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

2502.20633 2025-03-03 cs.LG 70%

Are LLMs Ready for Practical Adoption for Assertion Generation?

Vaishnavi Pulavarthi, Deeksha Nandal, Soham Dan, Debjit Pal

机构 * University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Microsoft（微软公司）

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

Comments 7 Pages, 9 Figures, Accepted in DATE 2025. arXiv admin note: substantial text overlap with arXiv:2406.18627

2502.20231 2025-02-28 cs.AI 70%

AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions

Clare Grogan, Jackie Kay, María Pérez-Ortiz

机构 * UCL（伦敦大学学院）； Google Deepmind（谷歌DeepMind）

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

2502.19672 2025-02-28 cs.CV cs.LG 70%

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack

Chenhe Gu, Jindong Gu, Andong Hua, Yao Qin

机构 * University of California, Irvine（加州大学欧文分校）； University of Oxford（牛津大学）； University of California, Santa Barbara（加州大学圣巴巴拉分校）

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

Comments arXiv admin note: text overlap with arXiv:2403.09766

2406.19859 2025-02-28 cs.AI cs.HC cs.MM 70%

MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Qi He, Wangmeng Xiang, Hanyuan Chen, Jin-Peng Lan, Xianhui Lin, Kang Zhu, Bin Luo, Yifeng Geng, Xuansong Xie, Alexander G. Hauptmann

机构 * Alibaba Group（阿里巴巴集团）； Carnegie Mellon University（卡内基梅隆大学）； University of Washington（华盛顿大学）； Tacoma School of Engineering & Technology (SET)（塔科马工程与技术学院）

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

Comments Accepted by ICLR 2025, Project: https://modelscope.cn/studios/WordArt/WordArt

2502.17903 2025-02-26 cs.AI cs.HC 70%

Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption

Lars Krupp, Daniel Geißler, Paul Lukowicz, Jakob Karolus

机构 * German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）； RPTU Kaiserslautern-Landau（凯泽斯劳滕-兰道莱茵-普法尔茨理工大学）

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

2502.16767 2025-02-25 cs.CL 70%

A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts

Jhon Rayo, Raul de la Rosa, Mario Garrido

机构 * Universidad de los Andes（洛斯安第斯大学）

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

Comments 5 pages; Workshop paper; Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)

Journal ref Proceedings of the 1st Regulatory NLP Workshop, RegNLP 2025, Abu Dhabi, UAE, vol. 1, January 2025, pp. 31-35

2502.15686 2025-02-25 cs.DB cs.CL 70%

V-SQL: A View-based Two-stage Text-to-SQL Framework

Zeshun You, Jiebin Yao, Dong Cheng, Zhiwei Wen, Zhiliang Lu, Xianyi Shen

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

Comments 10 pages,5 figures,

2405.16581 2025-02-25 cs.LG 70%

On Bits and Bandits: Quantifying the Regret-Information Trade-off

Itai Shufaro, Nadav Merlis, Nir Weinberger, Shie Mannor

机构 * Technion（以色列理工学院）； ENSAE（法国国立统计与经济管理学校）； NVIDIA Research（英伟达研究院）

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

2502.16147 2025-02-25 cs.CL 70%

Number Representations in LLMs: A Computational Parallel to Human Perception

H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Tatsuya Hiraoka, Ahmed Oumar El-Shangiti, Munachiso Nwadike, Kentaro Inui

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

Comments The number line of LLMs

2502.15583 2025-02-24 cs.CL 70%

Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid

Yunfeng Li, Jiqun Zhang, Guofu Liao, Xue Shi, Junhong Liu

机构 * Shenzhen University（深圳大学）； The University of Hong Kong（香港大学）

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

Comments 12 pages, 10 figures

2502.14170 2025-02-21 cs.LG cs.DC 70%

Blockchain-based Framework for Scalable and Incentivized Federated Learning

Bijun Wu, Oshani Seneviratne

机构 * Rensselaer Polytechnic Institute（伦斯勒理工学院）

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

2502.14095 2025-02-21 cs.CL 70%

Retrieving Versus Understanding Extractive Evidence in Few-Shot Learning

Karl Elbakian, Samuel Carton

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

Comments 9 pages, 8 figures, Accepted to AAAI 2025 Main Conference (AI Alignment Track)

2502.13983 2025-02-21 eess.AS cs.AI 70%

Gesture-Aware Zero-Shot Speech Recognition for Patients with Language Disorders

Seungbae Kim, Daeun Lee, Brielle Stark, Jinyoung Han

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

2310.03104 2025-02-21 cs.LG cs.CR 70%

Differentially Private Optimization for Non-Decomposable Objective Functions

Weiwei Kong, Andrés Muñoz Medina, Mónica Ribero

机构 * Google Research（谷歌研究院）

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

2502.13165 2025-02-20 cs.MA cs.AI q-fin.TR 70%

HedgeAgents: A Balanced-aware Multi-agent Financial Trading System

Xiangyu Li, Yawen Zeng, Xiaofen Xing, Jin Xu, Xiangmin Xu

机构 * South China University of Technology（华南理工大学）； ByteDance（字节跳动）； Pazhou Lab（琶洲实验室）

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

Comments This paper has been accepted by The Web Conference 2025 (WWW 2025) and selected for an oral presentation

2412.12072 2025-02-18 cs.CL 70%

Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats

Kuleen Sasse, Carlos Aguirre, Isabel Cachola, Sharon Levy, Mark Dredze

机构 * Johns Hopkins University（约翰斯·霍普金斯大学）； Rutgers University（罗格斯大学）

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

2502.09903 2025-02-17 cs.AI cs.HC cs.SE 70%

The Ann Arbor Architecture for Agent-Oriented Programming

Wei Dong

机构 * Ann Arbor Algorithms（安阿伯算法公司）

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

2502.08507 2025-02-13 cs.CL 70%

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction

Wei Li, Wen Luo, Guangyue Peng, Houfeng Wang

机构 * State Key Laboratory of Multimedia Information Processing（多媒体信息处理国家重点实验室）； School of Computer Science, Peking University（北京大学计算机学院）

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

Comments Accepted by NAACL 2025 main conference

2502.05150 2025-02-10 cs.CL 70%

CodeSCM: Causal Analysis for Multi-Modal Code Generation

Mukur Gupta, Noopur Bhatt, Suman Jana

机构 * Columbia University（哥伦比亚大学）

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

Comments Accepted to NAACL 2025

1. 其他LLM 12266 篇

Market-based Architectures in RL and Beyond

Learning to Generate Structured Output with Schema Reinforcement Learning

AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL

Neural machine translation system for Lezgian, Russian and Azerbaijani languages

AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding

AI Agents for Ground-Based Gamma Astronomy

Will AI replace Software Engineers? Do not hold your breath

ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining

The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community

Learning to Substitute Components for Compositional Generalization

The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents

Are LLMs Ready for Practical Adoption for Assertion Generation?

AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack

MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption

A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts

V-SQL: A View-based Two-stage Text-to-SQL Framework

On Bits and Bandits: Quantifying the Regret-Information Trade-off

Number Representations in LLMs: A Computational Parallel to Human Perception

Chats-Grid: An Iterative Retrieval Q&A Optimization Scheme Leveraging Large Model and Retrieval Enhancement Generation in smart grid

Blockchain-based Framework for Scalable and Incentivized Federated Learning

Retrieving Versus Understanding Extractive Evidence in Few-Shot Learning

Gesture-Aware Zero-Shot Speech Recognition for Patients with Language Disorders

Differentially Private Optimization for Non-Decomposable Objective Functions

HedgeAgents: A Balanced-aware Multi-agent Financial Trading System

Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats

The Ann Arbor Architecture for Agent-Oriented Programming

Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction

CodeSCM: Causal Analysis for Multi-Modal Code Generation