语言大模型 / LLM

Understanding Refusal in Language Models with Sparse Autoencoders

Wei Jie Yeo, Nirmalendu Prakash, Clement Neo, Roy Ka-Wei Lee, Erik Cambria, Ranjan Satapathy

机构 * Nanyang Technological University（南洋理工大学） ； Singapore University of Technology and Design（新加坡科技设计大学） ； Digital Trust Centre（数字信任中心） ； Institute of High Performance Computing (IHPC)（高性能计算研究所） 纠错

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

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration

Mingyang Song, Xiaoye Qu, Jiawei Zhou, Yu Cheng

机构 * Fudan University（复旦大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Stony Brook University（石溪大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments Accepted by CVPR 2025. Project Page: https://vlmlt.github.io/

Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing

Weixing Wang, Zifeng Ding, Jindong Gu, Rui Cao, Christoph Meinel, Gerard de Melo, Haojin Yang

机构 * Hasso Plattner Institute（霍普夫纳研究所） ； University of Potsdam（波茨坦大学） ； University of Cambridge（剑桥大学） ； University of Oxford（牛津大学） ； German University of Digital Science（德国数字科学大学） 纠错

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

Social Bias Probing: Fairness Benchmarking for Language Models

Marta Marchiori Manerba, Karolina Stańczak, Riccardo Guidotti, Isabelle Augenstein

机构 * University of Pisa（比萨大学） ； University of Copenhagen（哥本哈根大学） 纠错

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

Journal ref EMNLP 2024: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, 14653-14671

Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?

Yongjie Wang, Yibo Wang, Xin Zhou, Zhiqi Shen

机构 * Nanyang Technological University（南洋理工大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(title,abstract)；分类 cs.AI

Comments 18 Pages

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas

Ya Wu, Qiang Sheng, Danding Wang, Guang Yang, Yifan Sun, Zhengjia Wang, Yuyan Bu, Juan Cao

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

Comments 25 pages, 8 figures

The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect

Cosimo Iaia, Bhavin Choksi, Emily Wiebers, Gemma Roig, Christian J. Fiebach

机构 * Goethe University Frankfurt（弗赖堡歌德大学） ； Center for Brains, Minds and Machines, MIT Hessian.AI（大脑、心智与机器中心，MIT 荷尔斯泰因人工智能） ； Brain Imaging Center（脑成像中心） 纠错

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

Comments 13 pages, 4 Figures, 1 Table

TopoLM: brain-like spatio-functional organization in a topographic language model

Neil Rathi, Johannes Mehrer, Badr AlKhamissi, Taha Binhuraib, Nicholas M. Blauch, Martin Schrimpf

机构 * EPFL（瑞士联邦理工学院） ； Stanford University（斯坦福大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Harvard University（哈佛大学） 纠错

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

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

Yuchen Wang, Xuefeng Bai, Xiucheng Li, Weili Guan, Liqiang Nie, Xinyang Chen

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

Comments Accepted to ICML 2025

Universal language model with the intervention of quantum theory

D. -F. Qin

机构 * School of Physics and Electronic Science, East China Normal University（物理与电子科学学院，华东师范大学） 纠错

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

A Large Vision-Language Model based Environment Perception System for Visually Impaired People

Zezhou Chen, Zhaoxiang Liu, Kai Wang, Kohou Wang, Shiguo Lian

机构 * AI Innovation Center, China Unicom（中国unicom人工智能创新中心） ； Unicom Digital Technology, China Unicom（中国unicom数字技术） 纠错

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

Comments Accepted by IROS2024(9 pages, 8 figures)

Intrinsic Barriers to Explaining Deep Foundation Models

Zhen Tan, Huan Liu

机构 * Arizona State University（亚利桑那州立大学） 纠错

专题命中 知识编辑与模型理解 ：foundation model(title,abstract)；分类 cs.AI

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

Simon Schrodi, David T. Hoffmann, Max Argus, Volker Fischer, Thomas Brox

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

Comments ICLR 2025 (Oral)

Foundation models for electronic health records: representation dynamics and transferability

Michael C. Burkhart, Bashar Ramadan, Zewei Liao, Kaveri Chhikara, Juan C. Rojas, William F. Parker, Brett K. Beaulieu-Jones

专题命中 知识编辑与模型理解 ：foundation model(title,abstract)；分类 cs.LG

Summarization of Multimodal Presentations with Vision-Language Models: Study of the Effect of Modalities and Structure

Théo Gigant, Camille Guinaudeau, Frédéric Dufaux

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

Linguistic Interpretability of Transformer-based Language Models: a systematic review

Miguel López-Otal, Jorge Gracia, Jordi Bernad, Carlos Bobed, Lucía Pitarch-Ballesteros, Emma Anglés-Herrero

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

Comments Supplementary material: https://github.com/sid-unizar/ling-int-survey/blob/main/table.pdf

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning

Li An, Yujian Liu, Yepeng Liu, Yang Zhang, Yuheng Bu, Shiyu Chang

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

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models

Mingyang Wang, Heike Adel, Lukas Lange, Yihong Liu, Ercong Nie, Jannik Strötgen, Hinrich Schütze

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

Towards Understanding How Knowledge Evolves in Large Vision-Language Models

Sudong Wang, Yunjian Zhang, Yao Zhu, Jianing Li, Zizhe Wang, Yanwei Liu, Xiangyang Ji

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

Comments Accepted by CVPR 2025

EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability

Bryan Lim, Roman Huerta, Alejandro Sotelo, Anthonie Quintela, Priyanka Kumar

专题命中 知识编辑与模型理解 ：LLM(title,abstract)；分类 cs.AI

MMRL: Multi-Modal Representation Learning for Vision-Language Models

Yuncheng Guo, Xiaodong Gu

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

Comments Accepted by CVPR 2025

OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad

Luyao Tang, Yuxuan Yuan, Chaoqi Chen, Zeyu Zhang, Yue Huang, Kun Zhang

专题命中 知识编辑与模型理解 ：foundation model(title,abstract)；分类 cs.LG

Comments Accepted by CVPR 2025

EXPRESS: An LLM-Generated Explainable Property Valuation System with Neighbor Imputation

Wei-Wei Du, Yung-Chien Wang, Wen-Chih Peng

专题命中 知识编辑与模型理解 ：LLM(title,abstract)；分类 cs.LG

Comments Preprint

Boundary Prompting: Elastic Urban Region Representation via Graph-based Spatial Tokenization

Haojia Zhu, Jiahui Jin, Dong Kan, Rouxi Shen, Ruize Wang, Xiangguo Sun, Jinghui Zhang

专题命中 知识编辑与模型理解 ：prompting(title,abstract)；分类 cs.AI

Characterizing the Role of Similarity in the Property Inferences of Language Models

Juan Diego Rodriguez, Aaron Mueller, Kanishka Misra

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

Comments Published at NAACL 2025

On Fact and Frequency: LLM Responses to Misinformation Expressed with Uncertainty

Yana van de Sande, Gunes Açar, Thabo van Woudenberg, Martha Larson

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

Comments 4 pages, 1 figure, 3 tables, conference

Towards Effective Time-Aware Language Representation: Exploring Enhanced Temporal Understanding in Language Models

Jiexin Wang, Adam Jatowt, Yi Cai

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

Comments This paper has been accepted for publication in ACM Transactions on the Web. Final publication details (volume, issue, page range) will be updated once they are finalized

Developing a PET/CT Foundation Model for Cross-Modal Anatomical and Functional Imaging

Yujin Oh, Robert Seifert, Yihan Cao, Christoph Clement, Justin Ferdinandus, Constantin Lapa, Alessandro Liebich, Michelle Amon, Johanna Enke, Sifan Song, Runqi Meng, Fang Zeng, Ning Guo, Xiang Li, Pedram Heidari, Axel Rominger, Kuangyu Shi, Quanzheng Li

专题命中 知识编辑与模型理解 ：foundation model(title,abstract)；分类 cs.AI

Comments 11 pages, 2 figures, 3 tables

ECG-EmotionNet: Nested Mixture of Expert (NMoE) Adaptation of ECG-Foundation Model for Driver Emotion Recognition

Nastaran Mansourian, Arash Mohammadi, M. Omair Ahmad, M. N. S. Swamy

专题命中 知识编辑与模型理解 ：foundation model(title,abstract)；分类 cs.LG

Probing the limitations of multimodal language models for chemistry and materials research

Nawaf Alampara, Mara Schilling-Wilhelmi, Martiño Ríos-García, Indrajeet Mandal, Pranav Khetarpal, Hargun Singh Grover, N. M. Anoop Krishnan, Kevin Maik Jablonka

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