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 12169 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12169 篇

2509.25973 2025-10-01 cs.AI 83%

Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions

Junbeom Kim, Kyuyoung Kim, Jihoon Tack, Dongha Lim, Jinwoo Shin

机构 * KAIST AI(韩国科学技术院人工智能研究所) Yonsei University(延世大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23630 2025-09-30 cs.AI 83%

Game-Oriented ASR Error Correction via RAG-Enhanced LLM

Yan Jiang, Yongle Luo, Qixian Zhou, Elvis S. Liu

机构 * Tencent Games(腾讯游戏)

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

Journal ref 2025 IEEE Conference on Games (CoG), Lisbon, Portugal, 2025, pp. 1-8

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22447 2025-09-29 cs.AI cs.NE 83%

Guiding Evolution of Artificial Life Using Vision-Language Models

Nikhil Baid, Hannah Erlebach, Paul Hellegouarch, Frederico Wieser

机构 * University College London(伦敦大学学院) Institut Pasteur(巴斯德研究院)

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

Comments 9 pages, 6 figures. Accepted for publication in the Proceedings of the Artificial Life Conference 2025 (MIT Press)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09466 2025-09-22 cs.CR cs.CL 83%

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

机构 * Harbin Institute of Technology(哈尔滨工业大学) Singapore Management University(新加坡管理大学) National University of Singapore(国立新加坡大学)

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

Comments 19 pages, 6 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14031 2025-09-22 cs.NE cs.LG 83%

Modeling the Human Visual System: Comparative Insights from Response-Optimized and Task-Optimized Vision Models, Language Models, and different Readout Mechanisms

Shreya Saha, Ishaan Chadha, Meenakshi Khosla

机构 * Electrical and Computer Engineering University of California, San Diego(电气与计算机工程大学加州大学圣地亚哥分校) Halıcıoğlu Data Science Institute University of California, San Diego(Halıcıoğlu数据科学研究所大学加州大学圣地亚哥分校) Department of Cognitive Science, Department of Computer Science and Engineering University of California, San Diego(认知科学系计算机科学与工程系大学加州大学圣地亚哥分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16467 2025-09-17 cs.CL 83%

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández

机构 * Institute for Logic, Language and Computation, University of Amsterdam(逻辑、语言与计算研究所,阿姆斯特丹大学) Center for Language and Cognition, University of Groningen(语言与认知中心,格罗宁根大学)

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

Comments Accepted at EMNLP Main 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01042 2025-09-16 cs.LG 83%

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals

Peixuan Han, Cheng Qian, Xiusi Chen, Yuji Zhang, Heng Ji, Denghui Zhang

机构 * Siebel School of Computing(计算科学系) Data Science, University of Illinois Urbana-Champaign(数据科学,伊利诺伊大学厄巴纳-香槟分校) School of Business, Stevens Institute of Technology(商学院,史蒂文斯理工学院)

专题命中 其他LLM :LLM(title);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
2509.10963 2025-09-16 math.ST cs.AI stat.ME stat.TH 83%

Testing for LLM response differences: the case of a composite null consisting of semantically irrelevant query perturbations

Aranyak Acharyya, Carey E. Priebe, Hayden S. Helm

机构 * Mathematical Institute for Data Science(数据科学数学研究所) Department of Applied Mathematics and Statistics(应用数学与统计学系) Helivan

专题命中 其他LLM :LLM(title);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
2502.11451 2025-09-16 cs.CL 83%

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations

Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

机构 * National University of Singapore(国立新加坡大学) Singapore Management University(新加坡管理大学)

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

Comments Accepted by EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08203 2025-09-11 cs.HC cs.AI cs.SE 83%

Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units

Ryan Lingo, Rajeev Chhajer, Martin Arroyo, Luka Brkljacic, Ben Davis, Nithin Santhanam

机构 * Honda Research Institute, USA, Inc.(本田研究院(美国公司))

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

Comments 12 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.06286 2025-09-09 cs.LG 83%

RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations

Chang Xue, Youwei Lu, Chen Yang, Jinming Xing

机构 * Yeshiva University(耶鲁大学) Oklahoma State University(俄克拉荷马州立大学) Case Western Reserve University(凯斯西储大学) North Carolina State University(北卡罗来纳州立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20186 2025-08-29 cs.CR cs.AI cs.CY 83%

AI Propaganda factories with language models

Lukasz Olejnik

机构 * Department of War Studies(战争研究系) King's College London(伦敦国王学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09375 2025-08-26 cs.CL cs.SD eess.AS 83%

CoLMbo: Speaker Language Model for Descriptive Profiling

Massa Baali, Shuo Han, Syed Abdul Hannan, Purusottam Samal, Karanveer Singh, Soham Deshmukh, Rita Singh, Bhiksha Raj

机构 * Carnegie Mellon University(卡内基梅隆大学) FPrime AI

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

Comments Accepted to ASRU 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15510 2025-08-22 cs.AI 83%

Super-additive Cooperation in Language Model Agents

Filippo Tonini, Lukas Galke

机构 * University of Southern Denmark(丹麦南部大学)

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

Comments FAIEMA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.14805 2025-08-07 cs.CL 83%

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Julia Kharchenko, Tanya Roosta, Aman Chadha, Chirag Shah

机构 * University of Washington(华盛顿大学) UC Berkeley, Amazon(伯克利大学、亚马逊) Stanford University, Amazon GenAI(斯坦福大学、亚马逊生成人工智能)

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

Comments KDD 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19980 2025-07-30 cs.CL 83%

Exploring LLM Autoscoring Reliability in Large-Scale Writing Assessments Using Generalizability Theory

Dan Song, Won-Chan Lee, Hong Jiao

专题命中 其他LLM :LLM(title);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
2507.19537 2025-07-30 cs.CL 83%

Mind the Language Gap in Digital Humanities: LLM-Aided Translation of SKOS Thesauri

Felix Kraus, Nicolas Blumenröhr, Danah Tonne, Achim Streit

专题命中 其他LLM :LLM(title);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
2507.19283 2025-07-28 cs.IR cs.AI 83%

Towards LLM-Enhanced Group Recommender Systems

Sebastian Lubos, Alexander Felfernig, Thi Ngoc Trang Tran, Viet-Man Le, Damian Garber, Manuel Henrich, Reinhard Willfort, Jeremias Fuchs

机构 * Graz University of Technology(格拉茨技术大学)

专题命中 其他LLM :LLM(title);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
2507.18560 2025-07-25 q-fin.PM cs.AI 83%

HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization

Benjamin Coriat, Eric Benhamou

机构 * CentraleSupelec(中央理工-巴黎高等电子学院) Ai for Alpha IJCAI 2025 - FinLLM Workshop(IJCAI 2025 年 FinLLM 工作坊)

专题命中 其他LLM :LLM(title);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
2507.12207 2025-07-17 cs.AI cs.NE 83%

BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution

Subin Lin, Chuanbo Hua

机构 * Department of the Built Environment, National University of Singapore(新加坡国立大学建筑环境系) Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology(韩国科学技术院工业与系统工程系)

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

Comments ICML 2025 CO-Build Workshop Poster

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00718 2025-07-11 cs.LG cs.SD eess.AS 83%

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Isha Gupta, David Khachaturov, Robert Mullins

机构 * ETH Zürich(苏黎世联邦理工学院) University of Cambridge(剑桥大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06256 2025-07-10 cs.CR cs.AI cs.SD eess.AS 83%

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World

Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews, Lun Wang

机构 * Google DeepMind(谷歌DeepMind) The University of Maryland, College Park(马里兰大学 College Park分校)

专题命中 其他LLM :LLM(title);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
2506.08837 2025-06-30 cs.LG cs.CR 83%

Design Patterns for Securing LLM Agents against Prompt Injections

Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu, Edoardo Debenedetti, Daniel Dobos, Daniel Fabian, Marc Fischer, David Froelicher, Kathrin Grosse, Daniel Naeff, Ezinwanne Ozoani, Andrew Paverd, Florian Tramèr, Václav Volhejn

机构 * Invariant Labs IBM EPFL(苏黎世联邦理工学院) ETH Zurich(苏黎世联邦理工学院) Swisscom(瑞士通信) Google(谷歌) ETH AI Center(苏黎世联邦理工学院人工智能中心) AppliedAI Institute for Europe(欧洲应用AI研究院) Microsoft(微软) Lakera

专题命中 其他LLM :LLM(title);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
2504.05801 2025-06-30 cs.AI 83%

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM

Jianyu Liu, Yi Huang, Sheng Bi, Junlan Feng, Guilin Qi

机构 * School of Computer Science and Engineering, Southeast University, China(东南大学计算机科学与工程学院) Law and Innovation Lab, Law School, Southeast University, China(东南大学法学院创新实验室) China Mobile Research Institute, China(中国移动研究院)

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

Comments Proceedings of the 31st International Conference on Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14539 2025-06-27 cs.AI cs.CR 83%

Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack

Daewon Kang, YeongHwan Shin, Doyeon Kim, Kyu-Hwan Jung, Meong Hi Son

机构 * Research Institute for Future Medicine, Samsung Medical Center(未来医学研究所,三星医疗中心) Department of Digital Health, SAIHST, Sungkyunkwan University(数字健康系,SAIHST,成均馆大学) Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University(医疗设备管理与研究系,SAIHST,成均馆大学) Department of Emergency Medicine, Samsung Medical Center(急诊医学系,三星医疗中心)

专题命中 其他LLM :LLM(title);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
2410.18352 2025-06-24 cs.LG cs.CR cs.DC 83%

FedBaF: Federated Learning Aggregation Biased by a Foundation Model

Jong-Ik Park, Srinivasa Pranav, José M. F. Moura, Carlee Joe-Wong

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

Comments Published at The 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025)

Journal ref Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (2025), in Proceedings of Machine Learning Research 258:676-684

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17314 2025-06-24 cs.CL cs.HC 83%

PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights

Adnan Qidwai, Srija Mukhopadhyay, Prerana Khatiwada, Dan Roth, Vivek Gupta

机构 * IIIT Hyderabad(IIIT海得拉尔学院) University of Delaware(德雷塞尔大学) University of Pennsylvania(宾夕法尼亚大学) Arizona State University(亚利桑那州立大学)

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

Comments 9 Pages, 9 Figures. Accepted at ACL 2025 System Demonstration Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10715 2025-06-13 cs.CL 83%

Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet

Lorenzo Augello, John P. McCrae

机构 * Università Cattolica del Sacro Cuore(天主教圣心大学) Insight Research Ireland Centre for Data Analytics(爱尔兰洞察研究爱尔兰数据分析中心) University of Galway(Galway大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02480 2025-06-04 cs.CL 83%

ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities

Yifan Duan, Yihong Tang, Kehai Chen, Liqiang Nie, Min Zhang

机构 * Harbin Institute of Technology(哈尔滨工业大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17579 2025-06-04 cs.CL 83%

Leveraging Human Production-Interpretation Asymmetries to Test LLM Cognitive Plausibility

Suet-Ying Lam, Qingcheng Zeng, Jingyi Wu, Rob Voigt

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

Comments ACL 2025 Camera-ready

详情

展开后加载摘要…

URL PDF HTML 收藏