paper-with-me

Papers

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing

2024-02-16 · Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, failing to meet the requirements for lifelong editing. This study reveals a performance degradation encountered by knowledge editing in lifelong editing, characterized by toxicity buildup and toxicity flash, with the primary cause identified as pattern unmatch. We introduce a knowledge editing approach named Wise-Layer Knowledge Editor (WilKE), which selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. Experimental results demonstrate that, in lifelong editing, WilKE exhibits an average improvement of 46.2% and 67.8% on editing GPT2-XL and GPT-J relative to state-of-the-art knowledge editing methods.

📄 PDF Abstract BibTeX arXiv:2402.10987

Code (1)

chenhuihu/wilke 공식 구현 pytorch

Tasks

knowledge editing

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts

2024-11-23 · CVPR 2025 1 · Qizhou Chen, Chengyu Wang, Dakan Wang, Taolin Zhang 외

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenario…

knowledge editingMixture-of-ExpertsModel Editing

HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

2026-05-02 · Yuan Fang, Yi Xie, Xuming Ran arxiv

Large language models encode vast factual knowledge that can become outdated or incorrect after deployment, yet retraining is prohibitively costly. This motivates lifelong model editing, which updates targeted behavior w…

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning

2026-04-13 · Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu 외 arxiv

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter pertur…

Hierarchical Reinforcement Learning

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

2025-11-10 · Kunhao Li, Wenhao Li, Di Wu, Lei Yang 외 arxiv

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy le…

General Knowledge

UniAdapt: A Universal Adapter for Knowledge Calibration

2024-10-01 · Tai D. Nguyen, Long H. Pham, Jun Sun

Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challen…

Mixture-of-ExpertsModel EditingRetrieval-augmented GenerationSemantic Similarity+1