Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models

TL;DR

This paper introduces a context-aware unlearning method for large language models that effectively removes specific knowledge while preserving the model's ability to use that knowledge when reintroduced in prompts.

Contribution

It proposes a novel unlearning approach with a plug-in term to maintain contextual utility, addressing a key usability gap in existing methods.

Findings

Restores contextual utility to near original levels

Maintains effective forgetting of target knowledge

Preserves overall model utility

Abstract

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to remove specific knowledge while preserving overall model utility. Existing evaluations of unlearning methods focus on (1) the extent of forgetting of the target knowledge (forget set) and (2) maintaining performance on the retain set (i.e., utility). However, these evaluations overlook an important usability aspect: users may still want the model to leverage the removed information if it is re-introduced in the prompt. In a systematic evaluation of six state-of-the-art unlearning methods, we find that they consistently impair such contextual utility. To address this, we augment unlearning objectives with a plug-in term that preserves the model's ability to use forgotten knowledge when it is present in context. Extensive experiments demonstrate that our approach restores contextual utility to near original levels while still maintaining effective forgetting and retain-set utility.