Does Machine Unlearning Truly Remove Knowledge?
This work addresses the problem of ensuring data privacy and regulatory compliance in LLMs for researchers and practitioners, but it is incremental as it focuses on improving evaluation methods rather than introducing a new unlearning paradigm.
The paper tackles the challenge of evaluating machine unlearning algorithms for Large Language Models (LLMs) by introducing a comprehensive auditing framework with three benchmark datasets, six unlearning algorithms, and five prompt-based methods, and proposes a novel technique using intermediate activation perturbations to address limitations in existing auditing approaches.
In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attributed to large-scale architectures, which require extensive training on massive datasets. However, such datasets often contain sensitive or copyrighted content sourced from the public internet, raising concerns about data privacy and ownership. Regulatory frameworks, such as the General Data Protection Regulation (GDPR), grant individuals the right to request the removal of such sensitive information. This has motivated the development of machine unlearning algorithms that aim to remove specific knowledge from models without the need for costly retraining. Despite these advancements, evaluating the efficacy of unlearning algorithms remains a challenge due to the inherent complexity and generative nature of LLMs. In this work, we introduce a comprehensive auditing framework for unlearning evaluation, comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods. By using various auditing algorithms, we evaluate the effectiveness and robustness of different unlearning strategies. To explore alternatives beyond prompt-based auditing, we propose a novel technique that leverages intermediate activation perturbations, addressing the limitations of auditing methods that rely solely on model inputs and outputs.