CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept

YuXuan Wu, Bonaventure F. P. Dossou, Dianbo Liu

Keywords: machine unlearning, discrete representation, AI safety, LLM

TL;DR: Zero-Shot Unlearning of Large Language Models Using Discrete Representations

Abstract: Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine unlearning methods aim to remove specific information from models after training to address this. However, current approaches require additional model training or struggle to effectively erase particular data points and their associated context due to LLMs' complex, dense, and continuous nature. In this study, we propose a novel amortized unlearning approach using codebook features and Sparse Autoencoders (SAEs). By leveraging a bottleneck to decompose the activation space and regulate information flow, our method efficiently unlearns targeted information while preserving the model's performance on unrelated data. To the best of our knowledge, this is the first work that successfully enables unlearning specific topics with contextual relevance in an LLM, marking a significant step towards real-world applications of machine unlearning.

Submission Number: 92