Digital Forgetting in Large Language Models: A Survey of Unlearning Methods

arXiv:2404.02062v1 Announce Type: new
Abstract: The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations for forgetting include privacy protection, copyright protection, elimination of biases and discrimination, and prevention of harmful content generation. Effective digital forgetting has to be effective (meaning how well the new model has forgotten the undesired knowledge/behavior), retain the performance of the original model on the desirable tasks, …

arxiv biases copyright copyright protection cs.ai cs.cr cs.lg digital discrimination knowledge language language models large prevention privacy protection survey