语言大模型 / LLM

Reducing Tool Hallucination via Reliability Alignment

Hongshen Xu, Zichen Zhu, Lei Pan, Zihan Wang, Su Zhu, Da Ma, Ruisheng Cao, Lu Chen, Kai Yu

机构 * X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China.（上海交通大学计算机科学学院X-LANCE实验室） ； MoE Key Lab of Artificial Intelligence, Shanghai, China.（人工智能MoE重点实验室） ； Jiangsu Key Lab of Language Computing, Suzhou, China.（江苏语言计算重点实验室） ； Suzhou Laboratory, Suzhou, China.（苏州实验室） ； AISpeech Co., Ltd., Suzhou, China.（AISpeech公司） 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

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing

Yifan Lu, Jing Li, Yigeng Zhou, Yihui Zhang, Wenya Wang, Xiucheng Li, Meishan Zhang, Fangming Liu, Jun Yu, Min Zhang

机构 * Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）） ； Nanyang Technological University（南洋理工大学） ； Peng Cheng Laboratory（鹏城实验室） 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 ACL 2025 Findings

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models

Milan Bhan, Yann Choho, Pierre Moreau, Jean-Noel Vittaut, Nicolas Chesneau, Marie-Jeanne Lesot

机构 * Sorbonne Université, CNRS, LIP6（索邦大学、国家科学研究中心、LIP6） ； Ekimetrics 纠错

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

Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders

Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li, Phillip Howard, Vasudev Lal, Shao-Yen Tseng

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

Comments (Oral) CVPR 2025 Workshop on Mechanistic Interpretability for Vision. Authors 1 and 2 contributed equally

Interpreting token compositionality in LLMs: A robustness analysis

Nura Aljaafari, Danilo S. Carvalho, André Freitas

机构 * Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系） ； Idiap Research Institute（Idiap研究机构） ； National Biomarker Centre, CRUK-MI, Univ. of Manchester（国家生物标记中心，CRUK-MI，曼彻斯特大学） 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 23 pages, 3 Figures, 14 tables

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation

Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman, Nanshu Wang, Tengyu Xu, Alexander Radovic, Eryk Helenowski, Arya Talebzadeh, Aditya Tayade, Sinong Wang, Shafiq Joty, Han Fang, Hao Ma

机构 * HKUST(GZ)（香港科技大学（广州）） ； NTU（国立新加坡大学） ； GenAI, Meta（生成式人工智能，Meta） 纠错

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

Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selection

Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin

机构 * National Taiwan University（国立台湾大学） 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.LG

Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks

Christos Plachouras, Julien Guinot, George Fazekas, Elio Quinton, Emmanouil Benetos, Johan Pauwels

机构 * Queen Mary University of London（伦敦女王学院） ； Universal Music Group（环球音乐集团） 纠错

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

Comments Accepted at IJCNN 2025

Osiris: A Lightweight Open-Source Hallucination Detection System

Alex Shan, John Bauer, Christopher D. Manning

机构 * Stanford University（斯坦福大学） ； Stanford HAI（斯坦福HAI） 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 Stanford 191W

STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game

Eric Zhou, Shreyas Basavatia, Moontashir Siam, Zexin Chen, Mark O. Riedl

机构 * School of Interactive Computing, College of Computing（交互计算学院、计算机学院） 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.AI

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge

Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） 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 NAACL 2025 (main conference), Code: https://github.com/HanNight/AdaCAD

Using LLMs as prompt modifier to avoid biases in AI image generators

René Peinl

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

The quasi-semantic competence of LLMs: a case study on the part-whole relation

Mattia Proietti, Alessandro Lenci

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

Generating Structured Plan Representation of Procedures with LLMs

Deepeka Garg, Sihan Zeng, Sumitra Ganesh, Leo Ardon

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.AI

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service

Song Wang, Xun Wang, Jie Mei, Yujia Xie, Sean Muarray, Zhang Li, Lingfeng Wu, Si-Qing Chen, Wayne Xiong

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

A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis

Cristiano Patrício, Luís F. Teixeira, João C. Neves

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.LG

Comments Published in the Computational and Structural Biotechnology Journal

Standards for Belief Representations in LLMs

Daniel A. Herrmann, Benjamin A. Levinstein

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.AI

Journal ref Minds and Machines 35:5 (2025) 1-25

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning

Qizhou Chen, Taolin Zhang, Xiaofeng He, Dongyang Li, Chengyu Wang, Longtao Huang, Hui Xue

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 EMNLP 2024 main

Capturing Semantic Flow of ML-based Systems

Shin Yoo, Robert Feldt, Somin Kim, Naryeong Kim

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.LG

Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers

Zicong He, Boxuan Zhang, Lu Cheng

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

MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality

Shuaike Li, Kai Zhang, Qi Liu, Enhong Chen

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.AI

Steered Generation via Gradient Descent on Sparse Features

Sumanta Bhattacharyya, Pedram Rooshenas

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

Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?

Alimohammad Beigi, Bohan Jiang, Dawei Li, Zhen Tan, Pouya Shaeri, Tharindu Kumarage, Amrita Bhattacharjee, Huan Liu

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

Contrastive Localized Language-Image Pre-Training

Hong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang, Yinfei Yang, Zhe Gan

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

Comments Preprint

ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability

Ryuto Koike, Masahiro Kaneko, Ayana Niwa, Preslav Nakov, Naoaki Okazaki

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 Under Review

Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables

Xuzhao Geng, Haozhao Wang, Jun Wang, Wei Liu, Ruixuan Li

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

Assessing the Impact of the Quality of Textual Data on Feature Representation and Machine Learning Models

Tabinda Sarwar, Antonio Jose Jimeno Yepes, Lawrence Cavedon

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

Exploring Hierarchical Molecular Graph Representation in Multimodal LLMs

Chengxin Hu, Hao Li, Yihe Yuan, Jing Li, Ivor Tsang

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.LG

Comments 9 pages, 4 tables, 1 figure, paper under review

Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs

Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Jieyu Zhao, Salman Avestimehr

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

Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability

Ruixi Lin, Yang You

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