Unified Parameter-Efficient Unlearning for LLMs

TL;DR

This paper introduces LLMEraser, a novel framework for efficient, instance-wise unlearning in large language models that addresses privacy concerns without extensive retraining.

Contribution

The paper presents LLMEraser, a new unlearning method that uses influence functions for precise parameter adjustments, applicable across diverse unlearning tasks in LLMs.

Findings

LLMEraser effectively handles various unlearning scenarios.

It maintains model performance after unlearning.

The approach is efficient and scalable.

Abstract

The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domains, particularly through Parameter-Efficient Fine-Tuning (PEFT) strategies like LoRA, has become a prevalent practice due to its efficiency. However, this raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information. To address these issues, we introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise parameter adjustments using influence functions. Unlike traditional unlearning techniques that are often limited in scope and require extensive retraining, LLMEraser is designed to handle a broad spectrum of unlearning tasks without compromising model performance. Extensive experiments on benchmark datasets demonstrate that LLMEraser excels in efficiently managing various unlearning scenarios while maintaining the overall integrity and efficacy of the models.