The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework
"事实回忆" 相关文章
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
Mechanistic Unlearning: A New AI Method that Uses Mechanistic Interpretability to Localize and Edit Specific Model Components Associated with Factual Recall Mechanisms
