Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport

TL;DR

This paper introduces Opt-Out, a novel optimal transport-based method for entity-level unlearning in large language models, enabling effective removal of specific entity knowledge while maintaining overall model performance.

Contribution

The paper proposes a new unlearning technique using Wasserstein distance and introduces the first dataset for evaluating entity-level unlearning in LLMs.

Findings

Opt-Out outperforms existing unlearning methods.

It achieves more precise and effective removal of entity knowledge.

The method reduces the need for full model retraining.

Abstract

Instruction-following large language models (LLMs), such as ChatGPT, have become widely popular among everyday users. However, these models inadvertently disclose private, sensitive information to their users, underscoring the need for machine unlearning techniques to remove selective information from the models. While prior work has focused on forgetting small, random subsets of training data at the instance-level, we argue that real-world scenarios often require the removal of an entire user data, which may require a more careful maneuver. In this study, we explore entity-level unlearning, which aims to erase all knowledge related to a target entity while preserving the remaining model capabilities. To address this, we introduce Opt-Out, an optimal transport-based unlearning method that utilizes the Wasserstein distance from the model's initial parameters to achieve more effective and fine-grained unlearning. We also present the first Entity-Level Unlearning Dataset (ELUDe) designed to evaluate entity-level unlearning. Our empirical results demonstrate that Opt-Out surpasses existing methods, establishing a new standard for secure and adaptable LLMs that can accommodate user data removal requests without the need for full retraining.