语言大模型 / LLM - arXivDaily 专题

2409.00617 2024-09-04 cs.CL cs.AI 84%

Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models

Yifan Wei, Xiaoyan Yu, Yixuan Weng, Huanhuan Ma, Yuanzhe Zhang, Jun Zhao, Kang Liu

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

Comments CIKM 2024

2403.02889 2024-08-20 cs.CL cs.LG 84%

InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers

Yakir Yehuda, Itzik Malkiel, Oren Barkan, Jonathan Weill, Royi Ronen, Noam Koenigstein

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

Journal ref https://aclanthology.org/2024.acl-long.506/

2310.01469 2024-08-06 cs.CL cs.AI 84%

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Jia-Yu Yao, Kun-Peng Ning, Zhen-Hui Liu, Mu-Nan Ning, Yu-Yang Liu, Li Yuan

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

2408.00555 2024-08-02 cs.CV cs.AI cs.CL 84%

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation

Xiaoye Qu, Qiyuan Chen, Wei Wei, Jishuo Sun, Jianfeng Dong

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

2408.00550 2024-08-02 cs.CV cs.AI cs.CL 84%

Mitigating Multilingual Hallucination in Large Vision-Language Models

Xiaoye Qu, Mingyang Song, Wei Wei, Jianfeng Dong, Yu Cheng

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

2407.19842 2024-07-30 cs.LG cs.CL cs.CR 84%

Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability

Jorge García-Carrasco, Alejandro Maté, Juan Trujillo

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

Journal ref Proceedings of the Thirty-Third International Joint Converence on Artificial Intelligence, IJCAI 2024 (pp.385-393)

2403.09703 2024-07-01 cs.CL cs.AI 84%

Concept-aware Data Construction Improves In-context Learning of Language Models

Michal Štefánik, Marek Kadlčík, Petr Sojka

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

Comments Long paper to appear in Findings of ACL 2024

2307.00175 2024-06-28 cs.CL cs.LG 84%

Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks

B. A. Levinstein, Daniel A. Herrmann

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

2405.13907 2024-06-18 cs.CL cs.AI 84%

Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries

Adam Yang, Chen Chen, Konstantinos Pitas

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

2406.08402 2024-06-13 eess.AS cs.CL cs.LG cs.SD 84%

Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models

Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee

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

Comments Accepted to Interspeech 2024

2406.05798 2024-06-11 cs.CL cs.AI cs.NE 84%

Hidden Holes: topological aspects of language models

Stephen Fitz, Peter Romero, Jiyan Jonas Schneider

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

2405.12522 2024-05-22 cs.CL cs.LG 84%

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Charles O'Neill, Thang Bui

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

2310.08744 2024-05-07 cs.CL cs.LG 84%

Circuit Component Reuse Across Tasks in Transformer Language Models

Jack Merullo, Carsten Eickhoff, Ellie Pavlick

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

Comments Accepted at ICLR 2024

2404.12145 2024-04-19 cs.CL cs.AI 84%

From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency

Xenia Ohmer, Elia Bruni, Dieuwke Hupkes

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

2404.06948 2024-04-12 cs.CL cs.AI 84%

MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models

Rahul Mehta, Andrew Hoblitzell, Jack O'Keefe, Hyeju Jang, Vasudeva Varma

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

Comments Entry for SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes

2404.03044 2024-04-05 cs.LG cs.AI 84%

The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies

Marcin P. Joachimiak, Mark A. Miller, J. Harry Caufield, Ryan Ly, Nomi L. Harris, Andrew Tritt, Christopher J. Mungall, Kristofer E. Bouchard

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

2302.02060 2024-03-19 cs.CL cs.LG 84%

Representation Deficiency in Masked Language Modeling

Yu Meng, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han, Luke Zettlemoyer

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

Comments ICLR 2024

2403.03028 2024-03-06 cs.AI cs.CL 84%

Word Importance Explains How Prompts Affect Language Model Outputs

Stefan Hackmann, Haniyeh Mahmoudian, Mark Steadman, Michael Schmidt

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

2309.06991 2024-02-06 cs.LG cs.CL stat.ML 84%

Unsupervised Contrast-Consistent Ranking with Language Models

Niklas Stoehr, Pengxiang Cheng, Jing Wang, Daniel Preotiuc-Pietro, Rajarshi Bhowmik

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

Comments Long Paper at EACL 2024

2312.08027 2023-12-14 cs.CL cs.AI 84%

Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning

Jinta Weng, Jiarui Zhang, Yue Hu, Daidong Fa, Xiaofeng Xuand, Heyan Huang

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

Comments arXiv admin note: text overlap with arXiv:2210.16489

2311.10905 2023-11-21 cs.CL cs.AI 84%

Flexible Model Interpretability through Natural Language Model Editing

Karel D'Oosterlinck, Thomas Demeester, Chris Develder, Christopher Potts

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

Comments Extended Abstract -- work in progress. BlackboxNLP2023

2311.09053 2023-11-16 cs.CL cs.AI 84%

Assessing Knowledge Editing in Language Models via Relation Perspective

Yifan Wei, Xiaoyan Yu, Huanhuan Ma, Fangyu Lei, Yixuan Weng, Ran Song, Kang Liu

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

Comments Work in progress

2311.07383 2023-11-14 cs.CL cs.LG 84%

LM-Polygraph: Uncertainty Estimation for Language Models

Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, Artem Shelmanov

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

Comments Accepted at EMNLP-2023

2310.15910 2023-10-25 cs.CL cs.AI 84%

Characterizing Mechanisms for Factual Recall in Language Models

Qinan Yu, Jack Merullo, Ellie Pavlick

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

2212.14815 2023-09-19 cs.CL cs.LG 84%

Black-box language model explanation by context length probing

Ondřej Cífka, Antoine Liutkus

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

Comments 11 pages, 9 figures. ACL 2023 short paper camera-ready. Demos at https://cifkao.github.io/context-probing/ and https://huggingface.co/spaces/cifkao/context-probing ; code at https://github.com/cifkao/context-probing/

Journal ref Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2023), 1067--1079

2303.15430 2023-03-30 cs.CL cs.LG 84%

TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models

Md Kamrul Hasan, Md Saiful Islam, Sangwu Lee, Wasifur Rahman, Iftekhar Naim, Mohammed Ibrahim Khan, Ehsan Hoque

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

2210.06376 2022-10-13 cs.CL cs.AI 84%

Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary

Daniel Loureiro, Alípio Mário Jorge

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

2209.12153 2022-09-27 cs.CL cs.AI 84%

WinoDict: Probing language models for in-context word acquisition

Julian Martin Eisenschlos, Jeremy R. Cole, Fangyu Liu, William W. Cohen

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

2206.10744 2022-06-23 cs.CL cs.AI 84%

Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information

Tomasz Limisiewicz, David Mareček

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

Comments Presented at GeBNLP 2022

2204.10198 2022-04-25 cs.CL cs.AI 84%

Context-Aware Language Modeling for Goal-Oriented Dialogue Systems

Charlie Snell, Mengjiao Yang, Justin Fu, Yi Su, Sergey Levine

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

1. 知识编辑与模型理解 7539 篇

Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models

InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation

Mitigating Multilingual Hallucination in Large Vision-Language Models

Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability

Concept-aware Data Construction Improves In-context Learning of Language Models

Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks

Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries

Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models

Hidden Holes: topological aspects of language models

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Circuit Component Reuse Across Tasks in Transformer Language Models

From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency

MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models

The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies

Representation Deficiency in Masked Language Modeling

Word Importance Explains How Prompts Affect Language Model Outputs

Unsupervised Contrast-Consistent Ranking with Language Models

Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning

Flexible Model Interpretability through Natural Language Model Editing

Assessing Knowledge Editing in Language Models via Relation Perspective

LM-Polygraph: Uncertainty Estimation for Language Models

Characterizing Mechanisms for Factual Recall in Language Models

Black-box language model explanation by context length probing

TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models

Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary

WinoDict: Probing language models for in-context word acquisition

Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information

Context-Aware Language Modeling for Goal-Oriented Dialogue Systems