Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer.
Existing approaches achieve this objective at the cost of reasoning collapse, where the model fails to produce a coherent chain-of-thought (CoT) and does not properly terminate its reasoning process.
To address this challenge, we propose REDaCT (REgenerate via Detection and Corrective Tuning), an inference-time unlearning framework for LRMs.
REDaCT consists of two key components:
- a binary leak detector that identifies sentences in the reasoning trace that leak forget-set information,
- an embedding optimization module that learns a corrective embedding offline, such that when injected at the first detected leak during inference, it guides subsequent reasoning towards sentences that do not leak forget-set information.
Experimental results show that REDaCT completely avoids reasoning collapse, substantially improving reasoning preservation compared to state-of-the-art unlearning methods while maintaining perfect answer forgetting and near-perfect CoT forgetting.
Our code is available at: https://github.com/jmaccoby/redact.