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

2510.03762 2025-10-07 cs.CL 79%

Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs

Deshan Sumanathilaka, Nicholas Micallef, Julian Hough

机构 * Department of Computer Science, Swansea University(计算机科学系,萨斯奎汉大学)

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

Comments Paper accepted at GlobalNLP 2025: Workshop on beyond English: Natural Language Processing for All Languages in an Era of Large Language Models" 9 pages, 3 figures, 2 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23204 2025-09-30 cs.CL 79%

Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2

Stefan Arnold, René Gröbner

机构 * Friedrich-Alexander-Universität Erlangen-Nürnberg(埃朗根-纽伦堡弗里德里希-亚历山大大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22030 2025-09-29 cs.CL 79%

From Outliers to Topics in Language Models: Anticipating Trends in News Corpora

Evangelia Zve, Benjamin Icard, Alice Breton, Lila Sainero, Gauvain Bourgne, Jean-Gabriel Ganascia

机构 * LIP6, Sorbonne University, CNRS, France(LIP6,索邦大学,国家科学研究中心,法国)

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

Comments presented at ICNLSP 2025; to appear in the ACL Anthology; received the Best Full Paper Award

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.07733 2025-09-22 cs.CV cs.AI 79%

Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models

Patrick Knab, Sascha Marton, Christian Bartelt

机构 * Clausthal University of Technology(Clausthal 技术大学) University of Mannheim(曼海姆大学)

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

Comments ECAI 2025 - Main Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12497 2025-09-18 cs.LG 79%

Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model

Alessandro Crimi, Andrea Brovelli

机构 * AGH University of Krakow, Poland(克拉科夫AGH大学) Institut de Neurosciences de la Timone UMR 7289, Aix Marseille Université, CNRS, 13005, Marseille, France(里莫内神经科学研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.10723 2025-09-16 cs.HC cs.AI 79%

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight

Jingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang, Bingcan Guo, Ibrahim Khalilov, Simret Araya Gebreegziabher, Bingsheng Yao, Dakuo Wang, Yanfang Ye, Tianshi Li, Ziang Xiao, Yaxing Yao, Toby Jia-Jun Li

机构 * University of Notre Dame(诺丁汉大学) University of Michigan(密歇根大学) Northeastern University(东北大学) University of Washington(华盛顿大学) Johns Hopkins University(约翰霍普金斯大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.06130 2025-09-11 cs.CV cs.CL 79%

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia Sycara, Yaqi Xie

机构 * School of Computer Science, Carnegie Mellon University(计算机科学系,卡内基梅隆大学)

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

Comments Accepted by ICLR 2025. Project page: https://zhangce01.github.io/DeGF/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03025 2025-09-08 cs.CV cs.AI 79%

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens

Sohee Kim, Soohyun Ryu, Joonhyung Park, Eunho Yang

机构 * KAIST AI(韩国科学技术院人工智能研究所) AITRICS(人工智能与机器人技术研究所在线)

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

Comments accepted to EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15421 2025-08-22 cs.CL 79%

A Study of Privacy-preserving Language Modeling Approaches

Pritilata Saha, Abhirup Sinha

机构 * Paderborn University(帕德博恩大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12292 2025-08-19 cs.SD cs.AI eess.AS 79%

HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization

Hyebin Ahn, Kangwook Jang, Hoirin Kim

机构 * School of Electrical Engineering(电气工程学院)

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

Comments Accepted at Interspeech 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10295 2025-08-15 cs.CL 79%

Inductive Bias Extraction and Matching for LLM Prompts

Christian M. Angel, Francis Ferraro

机构 * Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County(计算机科学与电气工程系马里兰大学巴尔的摩县)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20850 2025-08-12 cs.CL 79%

Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models

Qing Yao, Kanishka Misra, Leonie Weissweiler, Kyle Mahowald

机构 * Department of Linguistics, The University of Texas at Austin(德克萨斯大学奥斯汀分校语言学系) Department of Linguistics and Philology, Uppsala University(乌普萨拉大学语言学与哲学系)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04787 2025-08-08 cs.HC cs.AI 79%

Evaluating the Impact of LLM-guided Reflection on Learning Outcomes with Interactive AI-Generated Educational Podcasts

Vishnu Menon, Andy Cherney, Elizabeth B. Cloude, Li Zhang, Tiffany D. Do

机构 * Drexel University(德雷塞尔大学) Michigan State University(密歇根州立大学)

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

Comments Accepted to NCME Special Interest Group on AI in Measurement: AIME-CON 2025 conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03991 2025-08-07 cs.AI 79%

Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents

Chongyu Bao, Ruimin Dai, Yangbo Shen, Runyang Jian, Jinghan Zhang, Xiaolan Liu, Kunpeng Liu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03654 2025-08-06 cs.CL cs.CV 79%

Can Large Vision-Language Models Understand Multimodal Sarcasm?

Xinyu Wang, Yue Zhang, Liqiang Jing

机构 * The University of Texas at Dallas(德克萨斯大学达拉斯分校)

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

Comments Accepted by CIKM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03524 2025-08-06 cs.CV cs.LG 79%

Semantic Mosaicing of Histo-Pathology Image Fragments using Visual Foundation Models

Stefan Brandstätter, Maximilian Köller, Philipp Seeböck, Alissa Blessing, Felicitas Oberndorfer, Svitlana Pochepnia, Helmut Prosch, Georg Langs

机构 * Computational Imaging Research Lab(计算成像研究实验室) Division of General and Pediatric Radiology(普通放射科与小儿放射科 division) Christian Doppler Laboratory for Machine Learning Driven Precision Imaging(Christian Doppler 机器学习驱动的精准成像实验室) Comprehensive Center for Artificial Intelligence in Medicine(医学人工智能综合中心) Department of Pathology(病理学系)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01380 2025-08-05 cs.CV cs.AI 79%

Effective Damage Data Generation by Fusing Imagery with Human Knowledge Using Vision-Language Models

Jie Wei, Erika Ardiles-Cruz, Aleksey Panasyuk, Erik Blasch

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

Comments 6 pages, IEEE NAECON'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06509 2025-08-04 cs.SE cs.AI 79%

Private GPTs for LLM-driven testing in software development and machine learning

Jakub Jagielski, Consuelo Rojas, Markus Abel

机构 * Ambrosys Gmbh(Ambrosys公司)

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

Comments 5 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02701 2025-07-22 cs.CL 79%

On Entity Identification in Language Models

Masaki Sakata, Benjamin Heinzerling, Sho Yokoi, Takumi Ito, Kentaro Inui

机构 * Tohoku University(东大大学) RIKEN(日本研究机构) NINJAL(日本国家情报机构) Langsmith Inc.(Langsmith公司) MBZUAI

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

Comments ACL 2025 Findings; 26 pages, 13 figures, 9 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14799 2025-07-22 cs.CR cs.AI 79%

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree

Sam Johnson, Viet Pham, Thai Le

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

Comments EMNLP 2025 System Demonstrations Submission

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.13761 2025-07-21 cs.CL 79%

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models

Palash Nandi, Maithili Joshi, Tanmoy Chakraborty

机构 * Department of Electrical Engineering(电气工程系) Indian Institute of Technology Delhi(印度理工学院德里)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.12443 2025-07-17 cs.NI cs.AI cs.HC cs.PL 79%

LLM-Based Config Synthesis requires Disambiguation

Rajdeep Mondal, Nikolaj Bjorner, Todd Millstein, Alan Tang, George Varghese

机构 * University of California Los Angeles(加州大学洛杉矶分校) Microsoft Research(微软研究院) Microsoft(微软)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.00043 2025-07-15 q-bio.BM cs.LG 79%

RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks

Rafael Josip Penić, Tin Vlašić, Roland G. Huber, Yue Wan, Mile Šikić

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

Comments 31 pages, 9 figures

Journal ref Nat. Commun. 16, 5671 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04509 2025-07-08 cs.CV cs.AI 79%

MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization

Zhendong Xiao, Wu Wei, Shujie Ji, Shan Yang, Changhao Chen

机构 * School of Automation Science and Engineering, South China University of Technology(自动化科学与工程学院,华南理工大学) Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)(人工智能方向,香港科学与技术大学(广州))

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

Comments PRCV

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16789 2025-06-26 cs.CL 79%

Conversational User-AI Intervention: A Study on Prompt Rewriting for Improved LLM Response Generation

Rupak Sarkar, Bahareh Sarrafzadeh, Nirupama Chandrasekaran, Nagu Rangan, Philip Resnik, Longqi Yang, Sujay Kumar Jauhar

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

Comments 8 pages, ACL style

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17073 2025-06-23 cs.CY cs.AI 79%

LLM-Based Bot Broadens the Range of Arguments in Online Discussions, Even When Transparently Disclosed as AI

Valeria Vuk, Cristina Sarasua, Fabrizio Gilardi

机构 * Department of Political Science University of Zurich(政治学系苏黎世大学) Department of Informatics University of Zurich(信息学系苏黎世大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15975 2025-06-23 cs.CR cs.CL 79%

Multi-use LLM Watermarking and the False Detection Problem

Zihao Fu, Chris Russell

机构 * Oxford Internet Institute(牛津互联网研究所) University of Oxford(牛津大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.04619 2025-06-18 cs.CL 79%

SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modeling

Xin Zhang, Qiyu Wei, Yingjie Zhu, Linhai Zhang, Deyu Zhou, Sophia Ananiadou

机构 * The University of Manchester(曼彻斯特大学) Harbin Institute of Technology(哈尔滨工业大学) King’s College London(伦敦大学国王学院) Southeast University(东南大学)

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

Comments Accepted at ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13028 2025-06-17 cs.OS cs.AI 79%

NaSh: Guardrails for an LLM-Powered Natural Language Shell

Bimal Raj Gyawali, Saikrishna Achalla, Konstantinos Kallas, Sam Kumar

机构 * University of California, Los Angeles(加州大学洛杉矶分校)

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

Comments 7 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12543 2025-06-17 cs.LG math.OC 79%

Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling

Teodora Srećković, Jonas Geiping, Antonio Orvieto

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) ELLIS Institute(ELLIS研究所) Tübingen AI Center(图宾根人工智能中心)

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

Comments Short version accepted at the 2025 HiLD Workshop at ICML

详情

展开后加载摘要…

URL PDF HTML 收藏