Forgetting-MarI: LLM Unlearning via Marginal Information Regularization

TL;DR

Forgetting-MarI is a novel LLM unlearning framework that selectively removes only the marginal information of specific data, ensuring privacy compliance while maintaining model performance.

Contribution

It introduces a provably effective unlearning method that bounds residual influence, outperforming existing techniques in reliability and performance preservation.

Findings

Outperforms current state-of-the-art unlearning methods

Provides provable guarantees of unlearning effectiveness

Maintains general model performance across benchmarks

Abstract

As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regulatory compliance. Unlearning addresses this challenge by selectively removing parametric knowledge from the trained models without retraining from scratch, which is critical for resource-intensive models such as Large Language Models (LLMs). Existing unlearning methods often degrade model performance by removing more information than necessary when attempting to ''forget'' specific data. We introduce Forgetting-MarI, an LLM unlearning framework that provably removes only the additional (marginal) information contributed by the data to be unlearned, while preserving the information supported by the data to be retained. By penalizing marginal information, our method yields an explicit upper bound on the unlearn dataset's residual influence in the trained models, providing provable undetectability. Extensive experiments confirm that our approach outperforms current state-of-the-art unlearning methods, delivering reliable forgetting and better preserved general model performance across diverse benchmarks. This advancement represents an important step toward making AI systems more controllable and compliant with privacy and copyright regulations without compromising their effectiveness.