RULE trains LLMs to refuse forgotten knowledge and answer permissible queries by optimizing a refusal boundary with reinforcement learning, beating baselines on forget quality and response naturalness with far less data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RULE: Reinforcement UnLEarning Achieves Forget-Retain Pareto Optimality
RULE trains LLMs to refuse forgotten knowledge and answer permissible queries by optimizing a refusal boundary with reinforcement learning, beating baselines on forget quality and response naturalness with far less data.