语言大模型 / LLM - arXivDaily 专题

2508.16697 2025-08-26 cs.CL cs.AI cs.LG 80%

QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso

机构 * JP Morgan AI Research（摩根大通人工智能研究）

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、cs.AI、cs.LG

2508.08285 2025-08-15 cs.CL cs.AI cs.LG 80%

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

Denis Janiak, Jakub Binkowski, Albert Sawczyn, Bogdan Gabrys, Ravid Shwartz-Ziv, Tomasz Kajdanowicz

机构 * Wroclaw University of Science and Technology（沃拉日市科学与技术大学）； University of Technology Sydney（悉尼技术大学）； New York University（纽约大学）

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、cs.AI、cs.LG

Comments Preprint, under review

2506.21573 2025-06-30 cs.CL cs.AI cs.LG 80%

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs

Yanwei Ren, Liu Liu, Baosheng Yu, Jiayan Qiu, Quan Chen

机构 * School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）； Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）； Nanyang Technological University（南洋理工大学）； University of Leicester（莱斯特大学）； Kuaishou Technology（快手科技）

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、cs.AI、cs.LG

2506.17419 2025-06-24 cs.CL cs.AI cs.LG stat.ML 80%

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making

Jinhao Duan, James Diffenderfer, Sandeep Madireddy, Tianlong Chen, Bhavya Kailkhura, Kaidi Xu

机构 * Drexel University（德雷塞尔大学）； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）； Argonne National Laboratory（阿贡国家实验室）； UNC Chapel Hill（北卡罗来纳大学教堂山分校）

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、cs.AI、cs.LG

Comments 19 pages, 5 figures, 4 tables

2506.12552 2025-06-17 cs.CL cs.AI cs.LG 80%

Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts

Zain Muhammad Mujahid, Dilshod Azizov, Maha Tufail Agro, Preslav Nakov

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； University of Copenhagen（哥本哈根大学）

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、cs.AI、cs.LG

Comments Accepted to Findings of the Association for Computational Linguistics (ACL) 2025

2407.21057 2025-06-13 cs.CL cs.AI cs.LG 80%

Multi-group Uncertainty Quantification for Long-form Text Generation

Terrance Liu, Zhiwei Steven Wu

机构 * Carnegie Mellon University（卡内基梅隆大学）

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、cs.AI、cs.LG

Comments Updated to UAI 2025 camera ready version

2505.23295 2025-05-30 cs.CL cs.AI cs.LG 80%

How Does Response Length Affect Long-Form Factuality

James Xu Zhao, Jimmy Z. J. Liu, Bryan Hooi, See-Kiong Ng

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、cs.AI、cs.LG

Comments ACL 2025 Findings. 24 pages, 10 figures, 18 tables. Code available at https://github.com/XuZhao0/length-bias-factuality

2503.20190 2025-03-27 cs.CV 80%

Cross-Modal Prototype Allocation: Unsupervised Slide Representation Learning via Patch-Text Contrast in Computational Pathology

Yuxuan Chen, Jiawen Li, Jiali Hu, Xitong Ling, Tian Guan, Anjia Han, Yonghong He

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

Comments 11pages,3 figures

2502.09858 2025-02-17 cs.LG cs.AI cs.CL q-bio.QM 80%

Automated Hypothesis Validation with Agentic Sequential Falsifications

Kexin Huang, Ying Jin, Ryan Li, Michael Y. Li, Emmanuel Candès, Jure Leskovec

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、cs.AI、cs.LG

2412.04806 2024-12-09 cs.LG cs.AI cs.CL 80%

Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning

Jayanie Bogahawatte, Sachith Seneviratne, Maneesha Perera, Saman Halgamuge

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、cs.AI、cs.LG

2404.08189 2024-12-03 cs.LG cs.AI cs.CL cs.IR 80%

Reducing hallucination in structured outputs via Retrieval-Augmented Generation

Patrice Béchard, Orlando Marquez Ayala

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、cs.AI、cs.LG

Comments To be presented at NAACL 2024. 11 pages and 4 figures

Journal ref 2024.naacl-industry.19

2405.01825 2024-08-27 cs.CV 80%

Improving Concept Alignment in Vision-Language Concept Bottleneck Models

Nithish Muthuchamy Selvaraj, Xiaobao Guo, Adams Wai-Kin Kong, Alex Kot

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

2408.04679 2024-08-12 cs.CL cs.AI cs.LG 80%

Towards Linguistic Neural Representation Learning and Sentence Retrieval from Electroencephalogram Recordings

Jinzhao Zhou, Yiqun Duan, Ziyi Zhao, Yu-Cheng Chang, Yu-Kai Wang, Thomas Do, Chin-Teng Lin

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、cs.AI、cs.LG

2406.02212 2024-06-05 cs.CE 80%

Generative Pre-Trained Diffusion Paradigm for Zero-Shot Time Series Forecasting

Jiarui Yang, Tao Dai, Naiqi Li, Junxi Wu, Peiyuan Liu, Jinmin Li, Jigang Bao, Haigang Zhang, Shutao Xia

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

2405.19893 2024-05-31 cs.LG cs.AI cs.CL 80%

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts

Chunjing Gan, Dan Yang, Binbin Hu, Hanxiao Zhang, Siyuan Li, Ziqi Liu, Yue Shen, Lin Ju, Zhiqiang Zhang, Jinjie Gu, Lei Liang, Jun Zhou

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、cs.AI、cs.LG

Comments 12 pages

2405.20003 2024-05-31 cs.LG cs.AI cs.CL 80%

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen

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、cs.AI、cs.LG

2405.18414 2024-05-29 cs.CL cs.AI cs.LG cs.SI 80%

Don't Forget to Connect! Improving RAG with Graph-based Reranking

Jialin Dong, Bahare Fatemi, Bryan Perozzi, Lin F. Yang, Anton Tsitsulin

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、cs.AI、cs.LG

2402.12219 2024-04-18 cs.CL cs.AI cs.LG 80%

Reformatted Alignment

Run-Ze Fan, Xuefeng Li, Haoyang Zou, Junlong Li, Shwai He, Ethan Chern, Jiewen Hu, Pengfei 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、cs.AI、cs.LG

Comments Homepage: https://gair-nlp.github.io/ReAlign/

2404.02935 2024-04-05 cs.CL cs.AI cs.LG 80%

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking

Jiawei Zhang, Chejian Xu, Yu Gai, Freddy Lecue, Dawn Song, Bo 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、cs.AI、cs.LG

2404.02904 2024-04-04 cs.CV cs.AI cs.CL cs.LG 80%

ALOHa: A New Measure for Hallucination in Captioning Models

Suzanne Petryk, David M. Chan, Anish Kachinthaya, Haodi Zou, John Canny, Joseph E. Gonzalez, Trevor Darrell

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、cs.AI、cs.LG

Comments To appear at NAACL 2024

2404.01588 2024-04-03 cs.CL cs.AI cs.LG 80%

Hallucination Diversity-Aware Active Learning for Text Summarization

Yu Xia, Xu Liu, Tong Yu, Sungchul Kim, Ryan A. Rossi, Anup Rao, Tung Mai, Shuai 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、cs.AI、cs.LG

Comments Accepted to NAACL 2024

2403.01548 2024-03-13 cs.CL cs.AI cs.LG 80%

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He

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、cs.AI、cs.LG

Comments code repo is available at: https://github.com/hkust-nlp/Activation_decoding.git

2402.03509 2024-02-07 cs.CL cs.AI cs.LG 80%

Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains

Sanjana Ramprasad, Kundan Krishna, Zachary C Lipton, Byron C Wallace

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

2312.10057 2023-12-19 cs.CY cs.HC 80%

Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work

Rishab Jain, Aditya Jain

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

Comments 10 pages, 6 figures

2310.09044 2023-10-16 cs.CL cs.AI cs.LG 80%

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

Sehyun Choi, Tianqing Fang, Zhaowei Wang, Yangqiu Song

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、cs.AI、cs.LG

Comments Accepted at EMNLP 2023 Main Conference

2305.03513 2023-09-20 cs.CL cs.AI cs.LG 80%

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs

Yucheng Shi, Hehuan Ma, Wenliang Zhong, Qiaoyu Tan, Gengchen Mai, Xiang Li, Tianming Liu, Junzhou Huang

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、cs.AI、cs.LG

Comments 6 pages, 2 figures

2305.13592 2023-06-13 cs.LG cs.AI cs.CL cs.CR cs.SE 80%

Understanding Programs by Exploiting (Fuzzing) Test Cases

Jianyu Zhao, Yuyang Rong, Yiwen Guo, Yifeng He, Hao 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.CL、cs.AI、cs.LG

Comments Findings of the Association for Computational Linguistics: ACL 2023; fix typos and update results to keep the same settings in all experiments

2302.09664 2023-04-18 cs.CL cs.AI cs.LG 80%

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

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.CL、cs.AI、cs.LG

Comments International Conference on Learning Representations 2023 (Spotlight)

2410.08255 2025-11-25 cs.LG cs.AI 80%

Investigating Representation Universality: Case Study on Genealogical Representations

探讨表示通用性：谱系表示的案例研究

David D. Baek, Yuxiao Li, Max Tegmark

机构 * MIT（麻省理工学院）

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、cs.LG

AI总结本研究探讨了大型语言模型在表示谱系信息时的通用性，通过两种实验证据验证图结构表示的通用性，并指出缺乏地面真实表示的挑战。

Comments 14 pages, 7 figures

Journal ref NeurIPS 2025 Workshop on Responsible Foundation Models

2510.11328 2025-10-14 cs.CL cs.AI 80%

Do LLMs "Feel"? Emotion Circuits Discovery and Control

Chenxi Wang, Yixuan Zhang, Ruiji Yu, Yufei Zheng, Lang Gao, Zirui Song, Zixiang Xu, Gus Xia, Huishuai Zhang, Dongyan Zhao, Xiuying Chen

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、cs.AI

Comments 19 pages, 8 figures, 8 tables. Code and dataset available at https://github.com/Aurora-cx/EmotionCircuits-LLM

1. 知识编辑与模型理解 7552 篇

QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making

Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts

Multi-group Uncertainty Quantification for Long-form Text Generation

How Does Response Length Affect Long-Form Factuality

Cross-Modal Prototype Allocation: Unsupervised Slide Representation Learning via Patch-Text Contrast in Computational Pathology

Automated Hypothesis Validation with Agentic Sequential Falsifications

Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning

Reducing hallucination in structured outputs via Retrieval-Augmented Generation

Improving Concept Alignment in Vision-Language Concept Bottleneck Models

Towards Linguistic Neural Representation Learning and Sentence Retrieval from Electroencephalogram Recordings

Generative Pre-Trained Diffusion Paradigm for Zero-Shot Time Series Forecasting

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Don't Forget to Connect! Improving RAG with Graph-based Reranking

Reformatted Alignment

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking

ALOHa: A New Measure for Hallucination in Captioning Models

Hallucination Diversity-Aware Active Learning for Text Summarization

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains

Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs

Understanding Programs by Exploiting (Fuzzing) Test Cases

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Investigating Representation Universality: Case Study on Genealogical Representations

Do LLMs "Feel"? Emotion Circuits Discovery and Control