PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning

Excerpt

arXiv:2606.18473v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. However, the boundary between knowledge to forget and knowledge to retain is often unclear, since related and even distant information may be entangled in the model. In this paper, we study LLM unlearning from a data-centric perspective and measure how unlearning effects propagate from the forget set to s