语言大模型 / LLM - arXivDaily 专题

2311.15296 2024-10-10 cs.CL 88%

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation

Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Peng Cheng, Zhonghao Wang, Haiying Deng

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

Comments Accepted by ACL 2024

2410.05085 2024-10-08 cs.CL 88%

Explanation sensitivity to the randomness of large language models: the case of journalistic text classification

Jeremie Bogaert, Marie-Catherine de Marneffe, Antonin Descampe, Louis Escouflaire, Cedrick Fairon, Francois-Xavier Standaert

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

Comments This paper is a faithful translation of a paper which was peer-reviewed and published in the French journal Traitement Automatique des Langues, n. 64

Journal ref Traitement Automatique des Langues 64, 2023, ATALA, Paris

2410.04819 2024-10-08 cs.CL 88%

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models

Kaichen Huang, Jiahao Huo, Yibo Yan, Kun Wang, Yutao Yue, Xuming Hu

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

2410.04045 2024-10-08 cs.CL 88%

Neuron-Level Sequential Editing for Large Language Models

Houcheng Jiang, Junfeng Fang, Tianyu Zhang, An Zhang, Ruipeng Wang, Tao Liang, Xiang Wang

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

2401.04700 2024-10-08 cs.CL 88%

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue

Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, Nanyun Peng

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

Comments Accepted by EMNLP 2024

2410.01457 2024-10-07 cs.LG 88%

Verbalized Graph Representation Learning: A Fully Interpretable Graph Model Based on Large Language Models Throughout the Entire Process

Xingyu Ji, Jiale Liu, Lu Li, Maojun Wang, Zeyu Zhang

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

Comments under review. corresponding author: Zeyu Zhang

2410.01280 2024-10-03 cs.LG 88%

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Can Demircan, Tankred Saanum, Akshay K. Jagadish, Marcel Binz, Eric Schulz

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

2308.00109 2024-09-05 cs.CL 88%

A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?

Evelina Leivada, Gary Marcus, Fritz Günther, Elliot Murphy

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

2408.12456 2024-08-23 cs.CL 88%

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing

Mengqi Zhang, Bowen Fang, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen, Liang Wang

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

2408.02503 2024-08-06 cs.CL 88%

UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model

Zhaowei Li, Wei Wang, YiQing Cai, Xu Qi, Pengyu Wang, Dong Zhang, Hang Song, Botian Jiang, Zhida Huang, Tao Wang

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

2408.01003 2024-08-05 cs.AI 88%

Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models

Kohou Wang, Xiang Liu, Zhaoxiang Liu, Kai Wang, Shiguo Lian

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

Comments 14 pages, 5 figures

2407.18999 2024-07-30 cs.CV cs.LG 88%

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models

Baao Xie, Qiuyu Chen, Yunnan Wang, Zequn Zhang, Xin Jin, Wenjun Zeng

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

Comments 9 pages, 7 figures

2407.09417 2024-07-23 cs.CL cs.IR 88%

Mitigating Entity-Level Hallucination in Large Language Models

Weihang Su, Yichen Tang, Qingyao Ai, Changyue Wang, Zhijing Wu, Yiqun Liu

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

2407.11409 2024-07-17 cs.CL 88%

Representation Bias in Political Sample Simulations with Large Language Models

Weihong Qi, Hanjia Lyu, Jiebo Luo

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

2407.08039 2024-07-12 cs.CL 88%

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

Yuji Zhang, Sha Li, Jiateng Liu, Pengfei Yu, Yi R. Fung, Jing Li, Manling Li, Heng Ji

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

2407.00668 2024-07-04 cs.CL 88%

HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability

Yanfang Chen, Ding Chen, Shichao Song, Simin Niu, Hanyu Wang, Zeyun Tang, Feiyu Xiong, Zhiyu Li

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

2406.17781 2024-06-27 cs.CV cs.AI cs.HC 88%

Large Language Models estimate fine-grained human color-concept associations

Kushin Mukherjee, Timothy T. Rogers, Karen B. Schloss

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

2405.02659 2024-06-26 cs.CL 88%

R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models

Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang, Longtao Huang, Hui Xue, Xiaofeng He, Jun Huang

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

Comments need to further experiment

2406.16033 2024-06-25 cs.CL 88%

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models

Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

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

2406.13184 2024-06-21 cs.CL 88%

Locating and Extracting Relational Concepts in Large Language Models

Zijian Wang, Britney White, Chang Xu

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

Journal ref Findings of ACL2024

2406.11267 2024-06-18 cs.CL 88%

Mitigating Large Language Model Hallucination with Faithful Finetuning

Minda Hu, Bowei He, Yufei Wang, Liangyou Li, Chen Ma, Irwin King

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

2406.10881 2024-06-18 cs.CL 88%

Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Lida Chen, Zujie Liang, Xintao Wang, Jiaqing Liang, Yanghua Xiao, Feng Wei, Jinglei Chen, Zhenghong Hao, Bing Han, Wei Wang

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

2406.09140 2024-06-14 cs.CL 88%

Investigating the translation capabilities of Large Language Models trained on parallel data only

Javier García Gilabert, Carlos Escolano, Aleix Sant Savall, Francesca De Luca Fornaciari, Audrey Mash, Xixian Liao, Maite Melero

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

Comments We release our code at: https://github.com/projecte-aina/Plume

2406.05883 2024-06-11 cs.LG cs.IT math.IT stat.ML 88%

Information Theoretic Guarantees For Policy Alignment In Large Language Models

Youssef Mroueh

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

2402.09656 2024-06-06 cs.AI 88%

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

Wanli Yang, Fei Sun, Xinyu Ma, Xun Liu, Dawei Yin, Xueqi Cheng

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

Comments Accepted at Findings of ACL 2024

2405.20588 2024-06-03 cs.CL 88%

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models

Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue, Jun Huang

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

Comments ACL2024 findings

2405.20081 2024-06-03 cs.CV cs.AI 88%

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models

Kai Wu, Boyuan Jiang, Zhengkai Jiang, Qingdong He, Donghao Luo, Shengzhi Wang, Qingwen Liu, Chengjie Wang

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

Comments 14 pages, 5 figures with supplementary material

2405.18027 2024-05-29 cs.CL 88%

TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models

Jaewoo Ahn, Taehyun Lee, Junyoung Lim, Jin-Hwa Kim, Sangdoo Yun, Hwaran Lee, Gunhee Kim

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

Comments ACL 2024 Findings. Code and dataset are released at https://ahnjaewoo.github.io/timechara

2405.14612 2024-05-29 cs.CV cs.AI 88%

Explaining Multi-modal Large Language Models by Analyzing their Vision Perception

Loris Giulivi, Giacomo Boracchi

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

Comments Submitted at BMVC 2024

2401.17623 2024-05-28 cs.CL 88%

Neighboring Perturbations of Knowledge Editing on Large Language Models

Jun-Yu Ma, Zhen-Hua Ling, Ningyu Zhang, Jia-Chen Gu

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

Comments Accepted by ICML 2024

1. 知识编辑与模型理解 7527 篇

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation

Explanation sensitivity to the randomness of large language models: the case of journalistic text classification

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models

Neuron-Level Sequential Editing for Large Language Models

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue

Verbalized Graph Representation Learning: A Fully Interpretable Graph Model Based on Large Language Models Throughout the Entire Process

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing

UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model

Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models

Mitigating Entity-Level Hallucination in Large Language Models

Representation Bias in Political Sample Simulations with Large Language Models

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability

Large Language Models estimate fine-grained human color-concept associations

R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models

Locating and Extracting Relational Concepts in Large Language Models

Mitigating Large Language Model Hallucination with Faithful Finetuning

Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals

Investigating the translation capabilities of Large Language Models trained on parallel data only

Information Theoretic Guarantees For Policy Alignment In Large Language Models

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models

TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models

Explaining Multi-modal Large Language Models by Analyzing their Vision Perception

Neighboring Perturbations of Knowledge Editing on Large Language Models