Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces

Yihuai Hong, Lei Yu, Haiqin Yang, Shauli Ravfogel, Mor Geva

Published: 05 Mar 2025, Last Modified: 05 Mar 2025ICLR 2025 Workshop Weight Space Learning PosterEveryoneRevisionsBibTeXCC BY 4.0
Track: long paper (up to 8 pages)
Keywords: LLM Safety, LLM Interpretability, LLM Unlearning, benchmark, evaluations
Submission Number: 29