语言大模型 / LLM - arXivDaily 专题

2502.17420 2026-02-10 cs.LG cs.AI cs.CL 90%

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

大语言模型中的拒绝几何学：概念锥与表征独立性

Tom Wollschläger, Jannes Elstner, Simon Geisler, Vincent Cohen-Addad, Stephan Günnemann, Johannes Gasteiger

机构 * School of Computation, Information \& Technology ； Munich Data Science Institute, Technical University of Munich ； Google Research ； Now at Google Research

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

AI总结本研究提出基于梯度的表征工程方法，揭示大语言模型拒绝行为的复杂空间结构及多维概念锥，证明多个独立机制驱动拒绝行为。

2510.04226 2026-01-29 cs.CL cs.AI cs.CY cs.IR cs.LG 90%

Epistemic Diversity and Knowledge Collapse in Large Language Models

知识多样性与大语言模型中的知识崩溃

Dustin Wright, Sarah Masud, Jared Moore, Srishti Yadav, Maria Antoniak, Peter Ebert Christensen, Chan Young Park, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学）； Aalborg University Copenhagen（奥胡斯大学哥本哈根分校）； Stanford University（斯坦福大学）； University of Colorado Boulder（科罗拉多大学波德分校）； Microsoft Research（微软研究院）

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

AI总结本研究通过评估大语言模型的知识多样性，发现模型大小影响多样性，RAG技术提升多样性，但文化背景影响显著，且国家特定信息更偏向英语。

Comments 16 pages; 8 figures, 4 tables; v2 changelog: Fixed the modeling for table 3, random effect is the model version; v3 changelog: Fixed minor formatting issues in tables 2 and 3; v4 changelog: Fixed some typos and model description; v5 changelog: Updated metadata; v6 changelog: Improved search baseline, writing revisions, added comparisons to semantic similarity only approaches

2601.13749 2026-01-21 cs.CL cs.AI cs.CY cs.LG 90%

Pro-AI Bias in Large Language Models

大语言模型中的亲AI偏见

Benaya Trabelsi, Jonathan Shaki, Sarit Kraus

机构 * Bar Ilan University（巴伊兰大学）

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

AI总结研究发现大语言模型存在亲AI偏见，表现为推荐AI相关选项、高估AI职位薪资及内部表示中AI的高相似性。

Comments 13 pages, 6 figures. Code available at: https://github.com/benayat/Pro-AI-bias-in-LLMs

2506.11938 2025-12-30 cs.CL cs.AI cs.LG 90%

Improving Large Language Model Safety with Contrastive Representation Learning

通过对比表征学习提升大语言模型安全性

Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin

机构 * ETH Zurich（苏黎世联邦理工学院）； MPI for Intelligent Systems（智能系统最大计划）； University of Toronto（多伦多大学）

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

AI总结本文提出基于对比表征学习的框架，通过三元组损失和对抗性难负样本挖掘提升大语言模型对对抗攻击的鲁棒性。

Comments EMNLP 2025 Main

2510.15691 2025-11-26 q-fin.CP cs.AI cs.CL cs.LG 90%

Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction

探索来自大语言模型的定量因素和新闻流表示的协同效应以预测股票收益率

Tian Guo, Emmanuel Hauptmann

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

AI总结本文提出融合学习框架和混合模型，利用大语言模型生成的定量因素和新闻流表示，提升股票收益率预测和选择的准确性。

2510.12029 2025-10-15 cs.CL cs.AI cs.LG 90%

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement

Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee

机构 * Department of Artificial Intelligence, Korea University（人工智能系，韩国大学）

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

Comments 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 7 pages, 2 figures

Journal ref 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Kuching, Malaysia, 2024, pp. 1604-1609

2509.07979 2025-10-13 cs.CV 90%

Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

机构 * KAIST AI（韩国科学技术院人工智能研究所）； New York University（纽约大学）； Chung-Ang University（Chung-Ang 大学）； Korea University（韩国大学）； ETH Zürich（苏黎世联邦理工学院）

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)；instruction tuning(abstract)

Comments Project Page: https://cvlab-kaist.github.io/VIRAL/

2508.17953 2025-08-26 cs.CL cs.AI cs.LG 90%

Understanding Subword Compositionality of Large Language Models

Qiwei Peng, Yekun Chai, Anders Søgaard

机构 * University of Copenhagen（哥本哈根大学）； ETH Zurich（苏黎世联邦理工学院）

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

Comments EMNLP 2025 Main

2502.06173 2025-08-18 cs.LG cs.AI cs.CL stat.AP stat.ML 90%

Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis

Sanket Jantre, Tianle Wang, Gilchan Park, Kriti Chopra, Nicholas Jeon, Xiaoning Qian, Nathan M. Urban, Byung-Jun Yoon

机构 * Computing & Data Sciences Directorate, Brookhaven National Laboratory（布鲁海文国家实验室计算与数据科学 Directorate）； Department of Electrical & Computer Engineering, Texas A&M University（德克萨斯A&M大学电气与计算机工程系）

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

2508.10192 2025-08-15 cs.CL cs.AI cs.LG q-fin.CP 90%

Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models

Igor Halperin

机构 * Fidelity Investments（fidelity投资公司）

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

Comments 24 pages, 3 figures

2506.21849 2025-06-30 cs.CL cs.AI cs.LG 90%

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models

Quan Xiao, Debarun Bhattacharjya, Balaji Ganesan, Radu Marinescu, Katsiaryna Mirylenka, Nhan H Pham, Michael Glass, Junkyu Lee

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院）； IBM Research（IBM研究院）； Zalando

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

Comments Accepted by The Conference on Uncertainty in Artificial Intelligence (UAI) 2025

2505.23854 2025-06-02 cs.CL cs.AI cs.LG 90%

Revisiting Uncertainty Estimation and Calibration of Large Language Models

Linwei Tao, Yi-Fan Yeh, Minjing Dong, Tao Huang, Philip Torr, Chang Xu

机构 * School of Computer Science University of Sydney（悉尼大学计算机科学学院）； City University of Hong Kong（香港城市大学）； Shanghai Jiao Tong University（上海交通大学）； Department of Engineering Science University of Oxford（牛津大学工程科学系）

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

2410.06981 2025-05-22 cs.LG cs.AI cs.CL 90%

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, Fazl Barez

机构 * Tangentic ； University of Oxford（牛津大学）； University of Delaware（德雷克塞尔大学）； MILA（蒙特利尔人工智能研究院）

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

2503.02080 2025-04-03 cs.CL cs.AI cs.CY cs.HC cs.LG 90%

Linear Representations of Political Perspective Emerge in Large Language Models

Junsol Kim, James Evans, Aaron Schein

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

Comments Published as a conference paper at ICLR 2025 https://openreview.net/forum?id=rwqShzb9li

2501.09929 2025-04-03 cs.LG cs.AI cs.CL 90%

Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Samuel Soo, Chen Guang, Wesley Teng, Chandrasekaran Balaganesh, Tan Guoxian, Yan Ming

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

Comments 9 maintext pages, 13 appendix pages

2503.08908 2025-03-13 cs.LG cs.AI cs.CL cs.CR 90%

Interpreting the Repeated Token Phenomenon in Large Language Models

Itay Yona, Ilia Shumailov, Jamie Hayes, Federico Barbero, Yossi Gandelsman

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

2503.05757 2025-03-11 cs.LG cs.AI cs.CL 90%

Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models

Prasenjit Dey, Srujana Merugu, Sivaramakrishnan Kaveri

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

Comments Proceedings of the ACM Web Conference 2025, WWW 25

2401.13835 2025-02-14 cs.LG cs.AI cs.CL cs.HC 90%

What Large Language Models Know and What People Think They Know

Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar, Catarina Belem, Sheer Karny, Xinyue Hu, Lukas Mayer, Padhraic Smyth

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

Comments 27 pages, 10 figures For the journal publication on Nature Machine Intelligence see https://www.nature.com/articles/s42256-024-00976-7 For the data and code see https://osf.io/y7pr6/

Journal ref Nat Mach Intell (2025)

2401.11817 2025-02-14 cs.CL cs.AI cs.LG 90%

Hallucination is Inevitable: An Innate Limitation of Large Language Models

Ziwei Xu, Sanjay Jain, Mohan Kankanhalli

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

2404.07066 2025-02-06 cs.CL cs.AI cs.LG 90%

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

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

Comments COLING 2025

2409.14459 2025-02-03 cs.CL cs.AI cs.LG 90%

Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis

Daoyang Li, Haiyan Zhao, Qingcheng Zeng, Mengnan Du

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

2405.14768 2024-12-20 cs.CL cs.AI cs.CV cs.IR cs.LG 90%

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models

Peng Wang, Zexi Li, Ningyu Zhang, Ziwen Xu, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

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

Comments NeurIPS 2024

2412.06007 2024-12-10 cs.NI 90%

Hallucination-aware Optimization for Large Language Model-empowered Communications

Yinqiu Liu, Guangyuan Liu, Ruichen Zhang, Dusit Niyato, Zehui Xiong, Dong In Kim, Kaibin Huang, Hongyang Du

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；preference optimization(abstract)

2401.01286 2024-11-19 cs.CL cs.AI cs.CV cs.HC cs.LG 90%

A Comprehensive Study of Knowledge Editing for Large Language Models

Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, Siyuan Cheng, Ziwen Xu, Xin Xu, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Ongoing work (v5): we have updated the Table 4 results after optimizing certain methods (related to AdaLoRA) and fixing computational bugs (related to ROME and MEMIT) in the EasyEdit. These improvements have led to better results than before. We will continue updating this paper and welcome everyone to discuss and exchange ideas

2402.03271 2024-11-14 cs.CL cs.AI cs.LG 90%

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi

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

Comments NeurIPS 2024

2403.18802 2024-11-08 cs.CL cs.AI cs.LG 90%

Long-form factuality in large language models

Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu, Nathan Hu, Jie Huang, Dustin Tran, Daiyi Peng, Ruibo Liu, Da Huang, Cosmo Du, Quoc V. Le

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

Comments NeurIPS 2024; 72 pages, 18 figures, 30 tables. Code at https://github.com/google-deepmind/long-form-factuality

2406.04331 2024-11-06 cs.CL cs.AI cs.IR cs.LG 90%

PaCE: Parsimonious Concept Engineering for Large Language Models

Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Darshan Thaker, Aditya Chattopadhyay, Chris Callison-Burch, René Vidal

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

Comments Accepted in NeurIPS 2024. GitHub repository at https://github.com/peterljq/Parsimonious-Concept-Engineering

2402.02392 2024-10-14 cs.AI cs.CL cs.LG 90%

DeLLMa: Decision Making Under Uncertainty with Large Language Models

Ollie Liu, Deqing Fu, Dani Yogatama, Willie Neiswanger

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

Comments 37 pages, 24 figures

2407.07071 2024-10-04 cs.CL cs.AI cs.LG 90%

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, James Glass

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

Comments EMNLP 2024 main conference long paper. The source code is available at https://github.com/voidism/Lookback-Lens

2409.13714 2024-09-24 cs.CL cs.AI cs.LG 90%

TracrBench: Generating Interpretability Testbeds with Large Language Models

Hannes Thurnherr, Jérémy Scheurer

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

Comments 6 pages + appendix, 4 figures, ICML Mechanistic Interpretability Workshop

1. 知识编辑与模型理解 7505 篇

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

Epistemic Diversity and Knowledge Collapse in Large Language Models

Pro-AI Bias in Large Language Models

Improving Large Language Model Safety with Contrastive Representation Learning

Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement

Visual Representation Alignment for Multimodal Large Language Models

Understanding Subword Compositionality of Large Language Models

Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis

Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models

Revisiting Uncertainty Estimation and Calibration of Large Language Models

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Linear Representations of Political Perspective Emerge in Large Language Models

Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Interpreting the Repeated Token Phenomenon in Large Language Models

Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models

What Large Language Models Know and What People Think They Know

Hallucination is Inevitable: An Innate Limitation of Large Language Models

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models

Hallucination-aware Optimization for Large Language Model-empowered Communications

A Comprehensive Study of Knowledge Editing for Large Language Models

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

Long-form factuality in large language models

PaCE: Parsimonious Concept Engineering for Large Language Models

DeLLMa: Decision Making Under Uncertainty with Large Language Models

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

TracrBench: Generating Interpretability Testbeds with Large Language Models