Kavli Affiliate: Jing Wang | First 5 Authors: Xiaopeng Li, Shasha Li, Shezheng Song, Huijun Liu, Bin Ji | Summary: The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updating a […]
Continue.. SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering