语言大模型 / LLM - arXivDaily 专题

2406.16416 2024-12-18 cs.CL 70%

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

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

Comments COLING 2025 (14 pages, 3 figures, 12 tables)

2412.11196 2024-12-17 cs.CL cs.CV 70%

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal

Yuhao Wang, Zhiyuan Zhu, Heyang Liu, Yusheng Liao, Hongcheng Liu, Yanfeng Wang, Yu Wang

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

2412.03516 2024-12-05 cs.AI 70%

You're (Not) My Type -- Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?

Dominic Lohr, Hieke Keuning, Natalie Kiesler

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

Comments Accepted at Journal of Computer Assisted Learning (2024)

2411.06638 2024-12-04 cs.SE cs.CL 70%

Model Editing for LLMs4Code: How Far are We?

Xiaopeng Li, Shangwen Wang, Shasha Li, Jun Ma, Jie Yu, Xiaodong Liu, Jing Wang, Bin Ji, Weimin Zhang

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

Comments Accepted by ICSE2025. The code is available at: https://github.com/xpq-tech/code-llmedit.git

2411.16205 2024-12-02 cs.CL 70%

MH-MoE: Multi-Head Mixture-of-Experts

Shaohan Huang, Xun Wu, Shuming Ma, Furu Wei

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

Comments 7 pages, 0 figures

2411.09968 2024-11-18 cs.CV cs.AI 70%

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs

Xiaofeng Zhang, Yihao Quan, Chaochen Gu, Chen Shen, Xiaosong Yuan, Shaotian Yan, Hao Cheng, Kaijie Wu, Jieping Ye

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

2411.08404 2024-11-14 q-fin.CP cs.LG 70%

Quantifying Qualitative Insights: Leveraging LLMs to Market Predict

Hoyoung Lee, Youngsoo Choi, Yuhee Kwon

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

Comments 7 pages, 4 figures

2307.12488 2024-11-14 cs.CR cs.AI 70%

How Does Naming Affect LLMs on Code Analysis Tasks?

Zhilong Wang, Lan Zhang, Chen Cao, Nanqing Luo, Xinzhi Luo, Peng Liu

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

Comments 3 Table, 8 figures

Journal ref Journal of Software Engineering and Applications. Vol.17 No.11, November 2024

2411.07213 2024-11-12 cs.LG 70%

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Madeline Brumley, Joe Kwon, David Krueger, Dmitrii Krasheninnikov, Usman Anwar

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

2402.03494 2024-11-12 cs.AI cs.RO 70%

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks

Xingpeng Sun, Haoming Meng, Souradip Chakraborty, Amrit Singh Bedi, Aniket Bera

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

Comments 30 pages, 7 figures

Journal ref Transactions on Machine Learning Research 2024

2409.00563 2024-11-12 cs.LG cs.SY eess.SY 70%

Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space Models

Emadeldeen Hamdan, Hongyi Pan, Ahmet Enis Cetin

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

2406.02378 2024-11-11 cs.CL 70%

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept

Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue, Xitong Zhang, Rongrong Wang, Jiliang Tang, Kristen Johnson

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

Comments 21 pages, 6 figures

2411.03978 2024-11-07 cs.LG 70%

Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning

Jiawei Yao, Qi Qian, Juhua Hu

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

Comments Accepted by NeurIPS 2024

2406.02550 2024-11-05 cs.LG cond-mat.dis-nn hep-th stat.ML 70%

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks

Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov

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

Comments Camera-ready version, NeurIPS 2024 (Oral)

2411.01213 2024-11-05 cs.CL 70%

One Arrow, Many Targets: Probing LLMs for Multi-Attribute Controllable Text Summarization

Tathagato Roy, Rahul Mishra

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

2310.13220 2024-11-04 cs.LG 70%

Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens

Ruifeng Ren, Yong Liu

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

Comments 35 pages

2407.02352 2024-10-30 cs.CL 70%

Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification

Pritish Sahu, Karan Sikka, Ajay Divakaran

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

2410.14276 2024-10-21 cs.CL 70%

EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding

Ching Ming Samuel Lau, Weiqi Wang, Haochen Shi, Baixuan Xu, Jiaxin Bai, Yangqiu Song

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

2410.13694 2024-10-18 cs.CV cs.CL 70%

Exploring the Design Space of Visual Context Representation in Video MLLMs

Yifan Du, Yuqi Huo, Kun Zhou, Zijia Zhao, Haoyu Lu, Han Huang, Wayne Xin Zhao, Bingning Wang, Weipeng Chen, Ji-Rong Wen

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

Comments Long Video MLLM; work in progress

2410.13274 2024-10-18 cs.CL 70%

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning

Minseok Choi, ChaeHun Park, Dohyun Lee, Jaegul Choo

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

Comments 16 pages, 5 figures

2410.10408 2024-10-15 cs.CL cs.IR 70%

Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion

Xinping Zhao, Jindi Yu, Zhenyu Liu, Jifang Wang, Dongfang Li, Yibin Chen, Baotian Hu, Min Zhang

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

Comments 12 pages, 3 figures, 6 tables. Accepted by EMNLP 2024's demo track

2410.05997 2024-10-10 eess.AS cs.CV cs.LG cs.SD 70%

An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution Alignment

Hugo Malard, Michel Olvera, Stéphane Lathuiliere, Slim Essid

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

2404.18533 2024-10-07 cs.AI cs.HC 70%

Evaluating Readability and Faithfulness of Concept-based Explanations

Meng Li, Haoran Jin, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, Xiting Wang

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

Comments EMNLP 2024; code: https://github.com/hr-jin/Concept-Explanation-Evaluation

2410.01079 2024-10-03 cs.CL 70%

Concept Space Alignment in Multilingual LLMs

Qiwei Peng, Anders Søgaard

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

Comments EMNLP 2024

2409.18743 2024-09-30 cs.RO cs.AI 70%

OpenObject-NAV: Open-Vocabulary Object-Oriented Navigation Based on Dynamic Carrier-Relationship Scene Graph

Yujie Tang, Meiling Wang, Yinan Deng, Zibo Zheng, Jiagui Zhong, Yufeng Yue

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

Comments Project website: https://openobject-nav.github.io/

2409.18679 2024-09-30 cs.CL 70%

"Why" Has the Least Side Effect on Model Editing

Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen

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

2406.17255 2024-09-27 cs.CL 70%

MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning

Zhenlong Dai, Chang Yao, WenKang Han, Ying Yuan, Zhipeng Gao, Jingyuan Chen

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

Comments Accepted by ACL 2024, Main Conference

2409.16727 2024-09-26 cs.CL 70%

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

Yihong Tang, Bo Wang, Xu Wang, Dongming Zhao, Jing Liu, Jijun Zhang, Ruifang He, Yuexian Hou

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

2409.15806 2024-09-25 cs.AI 70%

CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation

Fuxian Huang, Qi Zhang, Shaopeng Zhai, Jie Wang, Tianyi Zhang, Haoran Zhang, Ming Zhou, Yu Liu, Yu Qiao

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

2409.12194 2024-09-23 cs.CL cs.CY 70%

Gender Representation and Bias in Indian Civil Service Mock Interviews

Somonnoy Banerjee, Sujan Dutta, Soumyajit Datta, Ashiqur R. KhudaBukhsh

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

1. 知识编辑与模型理解 7552 篇

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal

You're (Not) My Type -- Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?

Model Editing for LLMs4Code: How Far are We?

MH-MoE: Multi-Head Mixture-of-Experts

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs

Quantifying Qualitative Insights: Leveraging LLMs to Market Predict

How Does Naming Affect LLMs on Code Analysis Tasks?

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks

Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space Models

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept

Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks

One Arrow, Many Targets: Probing LLMs for Multi-Attribute Controllable Text Summarization

Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens

Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification

EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding

Exploring the Design Space of Visual Context Representation in Video MLLMs

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning

Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion

An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution Alignment

Evaluating Readability and Faithfulness of Concept-based Explanations

Concept Space Alignment in Multilingual LLMs

OpenObject-NAV: Open-Vocabulary Object-Oriented Navigation Based on Dynamic Carrier-Relationship Scene Graph

"Why" Has the Least Side Effect on Model Editing

MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems

CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation

Gender Representation and Bias in Indian Civil Service Mock Interviews