| Title: |
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models |
| Authors: |
Geng, Jiahui, Li, Qing, Woisetschlaeger, Herbert, Chen, Zongxiong, Wang, Yuxia, Nakov, Preslav, Jacobsen, Hans-Arno, Karray, Fakhri |
| Publication Year: |
2025 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
| More Details: |
This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data (e.g., sensitive or illegal information) from LLMs, while preserving their overall utility without requiring full retraining. Despite growing research interest, there is no comprehensive survey that systematically organizes existing work and distills key insights; here, we aim to bridge this gap. We begin by introducing the definition and the paradigms of LLM unlearning, followed by a comprehensive taxonomy of existing unlearning studies. Next, we categorize current unlearning approaches, summarizing their strengths and limitations. Additionally, we review evaluation metrics and benchmarks, providing a structured overview of current assessment methodologies. Finally, we outline promising directions for future research, highlighting key challenges and opportunities in the field. |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2503.01854 |
| Accession Number: |
edsarx.2503.01854 |
| Database: |
arXiv |
