语言大模型 / LLM

Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models

Enming Zhang, Bingke Zhu, Yingying Chen, Qinghai Miao, Ming Tang, Jinqiao Wang

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心） ； Wuhan AI Research（武汉人工智能研究所） ； Peng Cheng Laboratory（鹏城实验室） 纠错

专题命中 知识编辑与模型理解 ：language model(title,abstract)

NormXLogit: The Head-on-Top Never Lies

Sina Abbasi, Mohammad Reza Modarres, Mohammad Taher Pilehvar

机构 * Tehran Institute for Advanced Studies, Khatam University, Iran（泰赫兰高级研究院，卡坦大学，伊朗） ； Cardiff University（卡迪夫大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Added comparisons on computational efficiency, included experiments on a new dataset with an additional evaluation metric for classification tasks, expanded explanations and discussions in the experiments, and presented a worked example for alignment metrics computation

CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection

Yue Wang, Liesheng Wei, Yuxiang Wang

机构 * Stanford University（斯坦福大学） ； College of Information Technology（信息科技学院） ； School of Business（商学院） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models

Ahmed Elshabrawy, Hour Kaing, Haiyue Song, Alham Fikri Aji, Hideki Tanaka, Masao Utiyama, Raj Dabre

机构 * MBZUAI（马克斯·普朗克人工智能研究所） ； NICT, Japan（日本信息通信技术研究所） ； IIT Madras（印度理工学院Madras分校） 纠错

专题命中 知识编辑与模型理解 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Lexiang Tang, Xianwei Zhuang, Bang Yang, Zhiyuan Hu, Hongxiang Li, Lu Ma, Jinghan Ru, Yuexian Zou

专题命中 知识编辑与模型理解 ：language model(abstract)

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders

Krishna Kanth Nakka

机构 * institutetext: Bavaria, Germany（巴伐利亚，德国） 纠错

专题命中 知识编辑与模型理解 ：foundation model(abstract)

Comments Accepted at Deep Breast Imaging workshop, MICCAI 2025

Large language models can replicate cross-cultural differences in personality

Paweł Niszczota, Mateusz Janczak, Michał Misiak

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

Comments 27 pages: 12 pages of manuscript + 15 pages of supplementary materials; in V3 added information that this is the Author Accepted Manuscript version; in V4 license changed to CC-BY

Journal ref Journal of Research in Personality, 115, 104584 (2025)

Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries

Kawin Mayilvaghanan, Siddhant Gupta, Ayush Kumar

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

Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement

Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Mahashweta Das

机构 * Visa Research（Visa研究） 纠错

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

Comments 11 pages, 10 figures

Word Meanings in Transformer Language Models

Jumbly Grindrod, Peter Grindrod

机构 * University of Reading, Department of Philosophy（reading大学哲学系） ； University of Oxford, Mathematical Institute（牛津大学数学研究所） 纠错

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

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Nathaniel Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter

机构 * Carnegie Mellon University（卡内基梅隆大学） ； University of Pennsylvania（宾夕法尼亚大学） ； Sony AI（索尼人工智能） ； Sony Group Corporation（索尼集团） ； Bosch Center for AI（博世人工智能中心） 纠错

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

Journal ref Transactions on Machine Learning Research (TMLR), 2025. ISSN 2835-8856

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） 纠错

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

Comments Accepted at Interspeech 2025

Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models

Jakub R. Kaczmarzyk, Sarah C. Van Alsten, Alyssa J. Cozzo, Rajarsi Gupta, Peter K. Koo, Melissa A. Troester, Katherine A. Hoadley, Joel H. Saltz

专题命中 其他LLM ：foundation model(title,abstract)

Every 28 Days the AI Dreams of Soft Skin and Burning Stars: Scaffolding AI Agents with Hormones and Emotions

Leigh Levinson, Christopher J. Agostino

机构 * Indiana University（印第安纳大学） ； NPC Worldwide（NPC全球） 纠错

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

Comments 9 pages, 1 figure, submitted to NeurIPS Creative AI track

New Interaction Paradigm for Complex EDA Software Leveraging GPT

Xinyu Wang, Boyu Han, Zhenghan Tai, Jingrui Tian, Yifan Wang, Junyu Yan, Yidong Tian

机构 * McGill University, Canada（麦吉尔大学） ； Stanford University, USA（斯坦福大学） ； University of Toronto, Canada（多伦多大学） ； Tsinghua University, China（清华大学） ； Beihang University, China（北航大学） ； The University of Manchester, UK（曼彻斯特大学） ； University of California, Los Angeles, USA（加州大学洛杉矶分校） ； Beijing Smarton Empower Co., Ltd., China（北京Smarton赋能科技有限公司） 纠错

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

Comments Accepted to ICML 2025 Workshop on New In Machine Learning (NewInML), 9 pages, 8 figures

Behavioral and Symbolic Fillers as Delay Mitigation for Embodied Conversational Agents in Virtual Reality

Denmar Mojan Gonzales, Snehanjali Kalamkar, Sophie Jörg, Jens Grubert

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Accepted to IEEE Transactions on Visualization and Computer Graphics

HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model

Qi Liu, Yabei Li, Hongsong Wang, Lei He

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

IntelliCap: Intelligent Guidance for Consistent View Sampling

Ayaka Yasunaga, Hideo Saito, Dieter Schmalstieg, Shohei Mori

机构 * Keio University（庆应大学） ； University of Stuttgart（斯图加特大学） 纠错

专题命中 其他LLM ：language model(abstract)

Comments This work is a pre-print version of a paper that has been accepted to the IEEE International Symposium on Mixed and Augmented Reality for future publication. Project Page: https://mediated-reality.github.io/projects/yasunaga_ismar25/

Security study based on the Chatgptplugin system: ldentifying Security Vulnerabilities

Ruomai Ren

专题命中 其他LLM ：language model(abstract)

Comments Master's thesis