arXiv cs.CL
· Papers
Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning
arXiv:2608.11408v1 Announce Type: new Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge is no longer expressed in their outputs. However, existing audits remain limited to one-off diagnostics: it is unclear whether th