conftrace_

hazardous knowledge

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

unlearning (2) large language model (2) invariant risk minimization (irm) (1) biosecurity (1) proxy measurement (1) wmdp benchmark (1) downstream fine-tuning (1) invariance (1)

Papers

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning ICML 2025 The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning ICML 2024