LGJul 26, 2025

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction

arXiv:2507.19894v13 citationsh-index: 8Has Code
Originality Synthesis-oriented
AI Analysis

This is an incremental work that organizes existing research for researchers in AI and privacy, but does not introduce new methods or results.

The paper provides a comprehensive survey on generative model unlearning (GenMU), addressing the lack of a unified framework by categorizing objectives, methods, and evaluation metrics, and it explores connections to related techniques while highlighting practical applications.

With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classification models to generative settings. Although notable progress has been made in this area, a unified framework for systematically organizing and integrating existing work is still lacking. The substantial differences among current studies in terms of unlearning objectives and evaluation protocols hinder the objective and fair comparison of various approaches. While some studies focus on specific types of generative models, they often overlook the commonalities and systematic characteristics inherent in Generative Model Unlearning (GenMU). To bridge this gap, we provide a comprehensive review of current research on GenMU and propose a unified analytical framework for categorizing unlearning objectives, methodological strategies, and evaluation metrics. In addition, we explore the connections between GenMU and related techniques, including model editing, reinforcement learning from human feedback, and controllable generation. We further highlight the potential practical value of unlearning techniques in real-world applications. Finally, we identify key challenges and outline future research directions aimed at laying a solid foundation for further advancements in this field. We consistently maintain the related open-source materials at https://github.com/caxLee/Generative-model-unlearning-survey.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes