paper-with-me

홈 › Papers

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

2023-10-03 · Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, Huajun Chen

As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's still a dark cloud lingering overhead -- will knowledge editing trigger butterfly effect? since it is still unclear whether knowledge editing might introduce side effects that pose potential risks or not. This paper pioneers the investigation into the potential pitfalls associated with knowledge editing for LLMs. To achieve this, we introduce new benchmark datasets and propose innovative evaluation metrics. Our results underline two pivotal concerns: (1) Knowledge Conflict: Editing groups of facts that logically clash can magnify the inherent inconsistencies in LLMs-a facet neglected by previous methods. (2) Knowledge Distortion: Altering parameters with the aim of editing factual knowledge can irrevocably warp the innate knowledge structure of LLMs. Experimental results vividly demonstrate that knowledge editing might inadvertently cast a shadow of unintended consequences on LLMs, which warrant attention and efforts for future works. Code and data are available at https://github.com/zjunlp/PitfallsKnowledgeEditing.

📄 PDF Abstract BibTeX arXiv:2310.02129

Code (1)

zjunlp/pitfallsknowledgeediting 공식 구현 pytorch

Tasks

knowledge editing

Similar Papers 제목 키워드 기반

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models

2024-06-03 · Cheng-Hsun Hsueh, Paul Kuo-Ming Huang, Tzu-Han Lin, Che-Wei Liao 외

Knowledge editing is a rising technique for efficiently updating factual knowledge in large language models (LLMs) with minimal alteration of parameters. However, recent studies have identified side effects, such as know…

knowledge editingSurvey

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models

2024-08-14 · Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu 외

Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong editing. This study explores the fundamen…

knowledge editing

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

2024-10-24 · Qi Li, Xiang Liu, Zhenheng Tang, Peijie Dong 외

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelli…

General KnowledgeModel Editing

Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks

2024-01-31 · Wenyue Hua, Jiang Guo, Mingwen Dong, Henghui Zhu 외

Current approaches of knowledge editing struggle to effectively propagate updates to interconnected facts. In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within thes…

counterfactualknowledge editingModel Editing

Unveiling Concept Attribution in Diffusion Models

2024-12-03 · Quang H. Nguyen, Hoang Phan, Khoa D. Doan

Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains black-box; little do we know about the role of its components in exhibi…

Model Editing