Exclusive Unlearning
This addresses safety risks for LLM users in sensitive domains like healthcare and education, but it is incremental as it builds on existing unlearning methods.
The paper tackles the challenge of preventing LLMs from generating harmful content in industrial applications by proposing Exclusive Unlearning, which broadly removes harmful knowledge while retaining specific domain capabilities, resulting in a model that ensures safety against diverse inputs like jailbreaks.
When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase specific harmful knowledge and expressions, diverse harmful content makes comprehensive removal difficult. In this study, instead of individually listing targets for forgetting, we propose Exclusive Unlearning (EU), which aims for broad harm removal by extensively forgetting everything except for the knowledge and expressions we wish to retain. We demonstrate that through Exclusive Unlearning, it is possible to obtain a model that ensures safety against a wide range of inputs, including jailbreaks, while maintaining the ability to respond to diverse instructions related to specific domains such as medicine and mathematics.