Enhance Lifelong Model Editing with Continuous Data-Adapter Association

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and lead to a significant forgetting effect after sequential edits over time, referred to as lifelong e...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-08
Hauptverfasser:	Li, Jiaang, Wang, Quan, Wang, Zhongnan, Zhang, Yongdong, Mao, Zhendong
Format:	Artikel
Sprache:	eng
Schlagworte:	Adapters Allocations Editing Freezing Knowledge management Large language models Parameter modification Parameter robustness Robustness Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!