Soft Prompting for Unlearning in Large Language Models

TL;DR

This paper introduces SPUL, a lightweight soft prompting method enabling large language models to unlearn specific data subsets at inference time, balancing utility and forgetting without updating model weights.

Contribution

The paper proposes a novel soft prompting framework, SPUL, for efficient unlearning in LLMs, offering a scalable and parameter-free alternative to fine-tuning methods.

Findings

SPUL effectively unlearns specific data with minimal utility loss.

The method scales across multiple LLM architectures.

Hyperparameter choices influence unlearning effectiveness.

Abstract

The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical and safety considerations when deploying these pre-trained models. In this work, we focus on investigating machine unlearning for LLMs motivated by data protection regulations. In contrast to the growing literature on fine-tuning methods to achieve unlearning, we focus on a comparatively lightweight alternative called soft prompting to realize the unlearning of a subset of training data. With losses designed to enforce forgetting as well as utility preservation, our framework \textbf{S}oft \textbf{P}rompting for \textbf{U}n\textbf{l}earning (SPUL) learns prompt tokens that can be appended to an arbitrary query to induce unlearning of specific examples at inference time without updating LLM parameters. We conduct a rigorous evaluation of the proposed method and our results indicate that SPUL can significantly improve the trade-off between utility and forgetting in the context of text classification and question answering with LLMs. We further validate our method using multiple LLMs to highlight the scalability of our framework and provide detailed insights into the choice of hyperparameters and the influence of the size of unlearning data. Our implementation is available at \url{https://github.com/karuna-bhaila/llm_unlearning}.