语言大模型 / LLM - arXivDaily 专题

2506.17296 2025-06-24 cs.CL cs.AI 86%

Semantic uncertainty in advanced decoding methods for LLM generation

Darius Foodeei, Simin Fan, Martin Jaggi

机构 * EPFL, Lausanne Switzerland（日内瓦联邦理工学院）

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

2406.18841 2025-06-17 cs.CY cs.AI cs.CL 86%

Navigating LLM Ethics: Advancements, Challenges, and Future Directions

Junfeng Jiao, Saleh Afroogh, Yiming Xu, Connor Phillips

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

2506.01114 2025-06-03 cs.LG cs.AI 86%

Reconsidering LLM Uncertainty Estimation Methods in the Wild

Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang, Tuo Zhang, Baturalp Buyukates, Salman Avestimehr, Sai Praneeth Karimireddy

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

Comments Accepted to ACL 2025

2505.22571 2025-06-02 cs.CL cs.AI cs.DB cs.IR 86%

Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems

Hoang Pham, Thuy-Duong Nguyen, Khac-Hoai Nam Bui

机构 * Viettel Group（越通集团）； Hanoi University of Science and Technology（河内科学技术大学）

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

2502.00602 2025-05-29 cs.CL cs.LG 86%

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Tianci Liu, Ruirui Li, Zihan Dong, Hui Liu, Xianfeng Tang, Qingyu Yin, Linjun Zhang, Haoyu Wang, Jing Gao

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

Comments ICML 2025

2505.18847 2025-05-27 cs.AI cs.CL 86%

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework

William Han, Chaojing Duan, Zhepeng Cen, Yihang Yao, Xiaoyu Song, Atharva Mhaskar, Dylan Leong, Michael A. Rosenberg, Emerson Liu, Ding Zhao

机构 * Carnegie Mellon University（卡内基梅隆大学）； Allegheny Health Network（阿勒格尼医疗网络）； University of Colorado（科罗拉多大学）

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

Comments 29 pages, 2 figures, 8 tables

2505.16113 2025-05-23 cs.LG cs.CL 86%

Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools

Panagiotis Lymperopoulos, Vasanth Sarathy

机构 * Tufts University（塔夫茨大学）

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

Comments 10 pages 3 figures 3 tables

2505.15710 2025-05-22 cs.CL cs.LG 86%

Advancing LLM Safe Alignment with Safety Representation Ranking

Tianqi Du, Zeming Wei, Quan Chen, Chenheng Zhang, Yisen Wang

机构 * State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室，智能科学与技术学院，北京大学）； School of Mathematical Sciences, Peking University（数学科学学院，北京大学）； Institute for Artificial Intelligence, Peking University（人工智能研究院，北京大学）

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

2505.07610 2025-05-20 cs.CL cs.AI 86%

Concept-Level Explainability for Auditing & Steering LLM Responses

Kenza Amara, Rita Sevastjanova, Mennatallah El-Assady

机构 * Department of Computer Science ETH Zurich（计算机科学系苏黎世联邦理工学院）

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

Comments 9 pages, 7 figures, Submission to Neurips 2025

2410.02707 2025-05-20 cs.CL cs.AI 86%

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Hadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart, Idan Szpektor, Hadas Kotek, Yonatan Belinkov

机构 * Technion（技术学院）； Google Research（谷歌研究）； Apple（苹果公司）

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

2403.08946 2025-05-20 cs.LG cs.CL cs.CY 86%

Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era

Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Lijie Hu, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu

机构 * University of Georgia（佐治亚大学）； New Jersey Institute of Technology（新泽西理工学院）； University of Virginia（弗吉尼亚大学）； Wake Forest University（威克森林大学）； King Abdullah University of Science and Technology（国王阿卜杜勒阿齐兹大学）； Amazon（亚马逊）

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

Comments 43 pages, 6 figures, including the latest works published in 2024-2025

2505.08200 2025-05-14 cs.CL cs.AI 86%

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun, Ivan Tsvigun, Zhuohan Xie, Igor Kiselev, Nico Daheim, Caiqi Zhang, Artem Vazhentsev, Mrinmaya Sachan, Preslav Nakov, Timothy Baldwin

机构 * MBZUAI ； ETH Zürich（苏黎世联邦理工学院）； University of Cambridge（剑桥大学）； Behavox ； Accenture ； Computational Semantics Group（语义计算小组）

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

2504.04462 2025-04-08 cs.CL cs.AI 86%

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability

David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros, Andrés Herrera-Poyatos, Virilo Tejedor, Francisco Herrera, Rosana Montes

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

Comments 25 pages and 3 figures

2406.04755 2025-03-03 cs.CR cs.AI cs.HC cs.LG 86%

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses

Weiran Lin, Anna Gerchanovsky, Omer Akgul, Lujo Bauer, Matt Fredrikson, Zifan Wang

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

2406.04344 2025-02-17 cs.LG cs.CL cs.CV 86%

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf, Weiyang Liu

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

Comments Published in Transactions on Machine Learning Research (116 pages, 32 figures, v3: refined the paper structure and added more empirical results)

2502.08109 2025-02-13 cs.CL cs.AI 86%

HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses

Sujeong Lee, Hayoung Lee, Seongsoo Heo, Wonik Choi

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

Comments 11 pages

2408.09172 2025-01-14 cs.AI cs.CL 86%

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection

Hsiu-Yuan Huang, Zichen Wu, Yutong Yang, Junzhao Zhang, Yunfang Wu

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

2402.09236 2024-12-10 cs.LG cs.AI math.ST stat.ML stat.TH 86%

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

Goutham Rajendran, Simon Buchholz, Bryon Aragam, Bernhard Schölkopf, Pradeep Ravikumar

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

Comments To appear in NeurIPS 2024 under the modified title 'From Causal to Concept-Based Representation Learning'

2412.00353 2024-12-09 cs.CL cs.AI 86%

Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection

Shanu Kumar, Saish Mendke, Karody Lubna Abdul Rahman, Santosh Kurasa, Parag Agrawal, Sandipan Dandapat

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

Comments Accepted in COLING 2025

2412.01033 2024-12-03 cs.CL cs.LG 86%

SAUP: Situation Awareness Uncertainty Propagation on LLM Agent

Qiwei Zhao, Xujiang Zhao, Yanchi Liu, Wei Cheng, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Huaxiu Yao, Haifeng Chen

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

2411.03486 2024-11-07 cs.AI cs.CL 86%

LLM Generated Distribution-Based Prediction of US Electoral Results, Part I

Caleb Bradshaw, Caelen Miller, Sean Warnick

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

Comments 17 pages, 10 Figures, Pre-print

2410.10866 2024-10-16 cs.CL cs.AI 86%

CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept

YuXuan Wu, Bonaventure F. P. Dossou, Dianbo Liu

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

2410.04277 2024-10-08 cs.CL cs.AI 86%

Mechanistic Behavior Editing of Language Models

Joykirat Singh, Subhabrata Dutta, Tanmoy Chakraborty

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

2409.17504 2024-09-27 cs.LG cs.CL 86%

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

Xuefeng Du, Chaowei Xiao, Yixuan Li

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

Comments NeurIPS 2024 Spotlight

2403.00781 2024-09-26 cs.IR cs.AI cs.LG cs.MM 86%

ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework

Zhongqi Yang, Elahe Khatibi, Nitish Nagesh, Mahyar Abbasian, Iman Azimi, Ramesh Jain, Amir M. Rahmani

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

Comments Published on Smart Health

Journal ref Smart Health 32 (2024): 100465

2409.09629 2024-09-24 cs.CL cs.AI 86%

Confidence Estimation for LLM-Based Dialogue State Tracking

Yi-Jyun Sun, Suvodip Dey, Dilek Hakkani-Tur, Gokhan Tur

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

Comments Accepted for publication at IEEE SLT 2024

2408.10811 2024-08-21 cs.CL cs.AI 86%

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

Chengzhi Zhong, Fei Cheng, Qianying Liu, Junfeng Jiang, Zhen Wan, Chenhui Chu, Yugo Murawaki, Sadao Kurohashi

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

Comments work in progress

2307.06865 2024-08-09 cs.CL cs.AI 86%

Effective Prompt Extraction from Language Models

Yiming Zhang, Nicholas Carlini, Daphne Ippolito

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

2406.04784 2024-06-10 cs.CL cs.AI 86%

SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

Ruihan Yang, Jiangjie Chen, Yikai Zhang, Siyu Yuan, Aili Chen, Kyle Richardson, Yanghua Xiao, Deqing Yang

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

Comments Preprint

2406.03487 2024-06-06 cs.CL cs.AI 86%

Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends

Sanjana Ramprasad, Elisa Ferracane, Zachary C. Lipton

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

Comments Accepted at ACL 2024

1. 知识编辑与模型理解 7539 篇

Semantic uncertainty in advanced decoding methods for LLM generation

Navigating LLM Ethics: Advancements, Challenges, and Future Directions

Reconsidering LLM Uncertainty Estimation Methods in the Wild

Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework

Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools

Advancing LLM Safe Alignment with Safety Representation Ranking

Concept-Level Explainability for Auditing & Steering LLM Responses

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability

LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection

SAUP: Situation Awareness Uncertainty Propagation on LLM Agent

LLM Generated Distribution-Based Prediction of US Electoral Results, Part I

CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept

Mechanistic Behavior Editing of Language Models

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework

Confidence Estimation for LLM-Based Dialogue State Tracking

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

Effective Prompt Extraction from Language Models

SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends