Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs

ACL ARR 2025 February Submission4782 Authors

Abstract: Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning is a promising approach to improve LLM safety by directly removing harmful behaviors and knowledge. In this paper, we propose "SPlit, UNlearn, MerGE" (SPUNGE), a framework that can be used with any unlearning method to amplify its effectiveness. SPUNGE leverages data attributes during unlearning by splitting unlearning data into subsets based on specific attribute values, unlearning each subset separately, and merging the unlearned models. We empirically demonstrate that SPUNGE significantly improves the performance of two recent unlearning methods for reducing undesirable behaviors and hazardous knowledge in two popular LLMs.

Paper Type: Short

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: model bias/unfairness mitigation, model bias/fairness evaluation

Languages Studied: English

Submission Number: 4782