Year: 2026
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institutions: Tohoku University, The University of Tokyo
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7151779565
Cites:
Cited by:
Related to: