语言大模型 / LLM - arXivDaily 专题

2503.10211 2025-03-14 cs.CL cs.SD eess.AS 85%

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation

Henglyu Liu, Andong Chen, Kehai Chen, Xuefeng Bai, Meizhi Zhong, Yuan Qiu, Min Zhang

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

Comments 12 pages, 7 figures

2406.00799 2025-03-07 cs.CR cs.CL cs.CY 85%

Get my drift? Catching LLM Task Drift with Activation Deltas

Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd

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

Comments SaTML 2025

2503.00724 2025-03-04 cs.CL 85%

Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies

Tianyi Huang, Jingyuan Yi, Peiyang Yu, Xiaochuan Xu

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

2502.16143 2025-02-25 cs.CL 85%

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination

Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi R. Fung, Kathleen McKeown, Chengxiang Zhai, Manling Li, Heng Ji

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

Comments 19 pages, 5 figures

2502.14273 2025-02-21 cs.CV cs.AI cs.MM 85%

LLM-EvRep: Learning an LLM-Compatible Event Representation Using a Self-Supervised Framework

Zongyou Yu, Qiang Qu, Qian Zhang, Nan Zhang, Xiaoming 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.AI

Comments 6 pages, 2 figures,Companion Proceedings of the ACM Web Conference 2025 (WWW Companion '25)

2502.08631 2025-02-20 cs.AI 85%

Ensemble based approach to quantifying uncertainty of LLM based classifications

Srijith Rajamohan, Ahmed Salhin, Josh Frazier, Rohit Kumar, Yu-Cheng Tsai, Todd Cook

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

2502.10406 2025-02-18 cs.CY cs.AI 85%

FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform Sellers

Dexin Kong, Xu Yan, Ming Chen, Shuguang Han, Jufeng Chen, Fei Huang

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

2410.14975 2025-02-11 cs.CV cs.AI 85%

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation

Jihyo Kim, Seulbi Lee, Sangheum Hwang

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

Comments Accepted at ICLR 2025. The first two authors contributed equally

2410.11781 2025-02-04 cs.LG 85%

Language Models Encode Numbers Using Digit Representations in Base 10

Amit Arnold Levy, Mor Geva

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.LG

Comments Accepted at NAACL 2025

2408.09916 2025-01-24 cs.CV cs.CL 85%

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit

Qizhou Chen, Taolin Zhang, Chengyu Wang, Xiaofeng He, Dakan Wang, Tingting 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

Comments Accepted to AAAI-2025 as an oral presentation

2303.00333 2024-12-24 cs.CL 85%

Competence-Based Analysis of Language Models

Adam Davies, Jize Jiang, ChengXiang Zhai

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

2412.07965 2024-12-12 cs.CL 85%

HalluCana: Fixing LLM Hallucination with A Canary Lookahead

Tianyi Li, Erenay Dayanik, Shubhi Tyagi, Andrea Pierleoni

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

2309.06799 2024-11-13 cs.AI physics.geo-ph 85%

When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System

Hao Zhang, Jin-Jian Xu, Hong-Wei Cui, Lin Li, Yaowen Yang, Chao-Sheng Tang, Niklas Boers

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

Comments accpeted by IEEE Geoscience and Remote Sensing Magazine

Journal ref IEEE Geoscience and Remote Sensing Magazine, 2024

2407.16434 2024-11-01 cs.CL 85%

Enhancing LLM's Cognition via Structurization

Kai Liu, Zhihang Fu, Chao Chen, Wei Zhang, Rongxin Jiang, Fan Zhou, Yaowu Chen, Yue Wu, Jieping Ye

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

Comments This paper has been accepted by NeurIPS 2024. Code is available at https://github.com/alibaba/struxgpt

2410.14262 2024-10-28 cs.CR cs.CL 85%

Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation

Ted Kwartler, Matthew Berman, Alan Aqrawi

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

2410.16489 2024-10-23 cs.LG 85%

LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling

Can Chen, Gabriel Oliveira, Hossein Sharifi Noghabi, Tristan Sylvain

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.LG

Comments 18 pages, 13 figures, 18 tables

2406.12277 2024-10-10 cs.CL 85%

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

Xin Zhao, Naoki Yoshinaga, Daisuke Oba

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

Comments 29 pages, 8 figures, 25 tables, Accepted by EMNLP 2024 (Findings)

2410.00363 2024-10-02 cs.CL 85%

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models

Shitian Zhao, Renrui Zhang, Xu Luo, Yan Wang, Shanghang Zhang, Peng Gao

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

2407.03282 2024-10-01 cs.CL 85%

LLM Internal States Reveal Hallucination Risk Faced With a Query

Ziwei Ji, Delong Chen, Etsuko Ishii, Samuel Cahyawijaya, Yejin Bang, Bryan Wilie, Pascale Fung

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

2409.14144 2024-09-24 cs.CL 85%

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

Zeping Yu, Sophia Ananiadou

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

Comments Accepted by EMNLP 2024 main. Mechanistic interpretability for arithmetic tasks in large language models

2305.14795 2024-09-10 cs.CL 85%

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning, Christopher Potts, Danqi Chen

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

Comments EMNLP 2023. Our code and datasets are available at https://github.com/princeton-nlp/MQuAKE

2408.09798 2024-08-20 cs.LG 85%

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

Yun-Da Tsai, Ting-Yu Yen, Keng-Te Liao, Shou-De Lin

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

Comments arXiv admin note: text overlap with arXiv:2407.05036

2407.13442 2024-07-19 cs.CV cs.CL 85%

BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models

Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi, Tae-Hyun Oh

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

Comments Accepted at ECCV 2024. [Project Pages] https://beafbench.github.io/

2407.13237 2024-07-19 cs.AI 85%

LLM-Empowered State Representation for Reinforcement Learning

Boyuan Wang, Yun Qu, Yuhang Jiang, Jianzhun Shao, Chang Liu, Wenming Yang, Xiangyang Ji

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

2402.10426 2024-07-08 cs.CL 85%

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection

Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, Minnan Luo

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

2405.10548 2024-06-13 cs.CL 85%

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks

Anwoy Chatterjee, Eshaan Tanwar, 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

Comments Accepted at ACL 2024 Main

2406.04854 2024-06-10 cs.CL 85%

Uncertainty Aware Learning for Language Model Alignment

Yikun Wang, Rui Zheng, Liang Ding, Qi Zhang, Dahua Lin, Dacheng Tao

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

Comments ACL 2024

2405.00301 2024-06-10 cs.CL 85%

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

Farima Fatahi Bayat, Xin Liu, H. V. Jagadish, Lu Wang

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

Comments ACL 2024 Findings (Long paper)

2405.20434 2024-06-03 cs.HC cs.AI 85%

Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions

Hyo Jin Do, Rachel Ostrand, Justin D. Weisz, Casey Dugan, Prasanna Sattigeri, Dennis Wei, Keerthiram Murugesan, Werner Geyer

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

Comments Submitted to the Trust and Reliance in Evolving Human-AI Workflows (TREW) Workshop at CHI 2024

2405.03207 2024-05-07 cs.CL 85%

A Philosophical Introduction to Language Models - Part II: The Way Forward

Raphaël Millière, Cameron Buckner

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

1. 知识编辑与模型理解 7596 篇

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation

Get my drift? Catching LLM Task Drift with Activation Deltas

Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination

LLM-EvRep: Learning an LLM-Compatible Event Representation Using a Self-Supervised Framework

Ensemble based approach to quantifying uncertainty of LLM based classifications

FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform Sellers

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation

Language Models Encode Numbers Using Digit Representations in Base 10

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit

Competence-Based Analysis of Language Models

HalluCana: Fixing LLM Hallucination with A Canary Lookahead

When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System

Enhancing LLM's Cognition via Structurization

Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation

LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models

LLM Internal States Reveal Hallucination Risk Faced With a Query

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models

LLM-Empowered State Representation for Reinforcement Learning

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks

Uncertainty Aware Learning for Language Model Alignment

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions

A Philosophical Introduction to Language Models - Part II: The Way Forward