The Frontier of Data Erasure: A Survey on Machine Unlearning for Large Language Models
This article reviews the latest in machine unlearning for large language models (LLMs), introducing methods for the targeted forgetting of information to address privacy, ethical, and legal challenges without necessitating full-model retraining. Machine unlearning is a cutting-edge solution, mitigating risk concerns of LLMs and artificial intelligence.
Authors
- Tianqing Zhu (ORCID: https://orcid.org/0000-0003-3411-7947)
- Youyang Qu (ORCID: https://orcid.org/0000-0002-2944-4647)
- Nan Sun (ORCID: https://orcid.org/0000-0001-9123-9022)
- Kanchana Thilakarathna (ORCID: https://orcid.org/0000-0003-4332-0082)
- Ming Ding (ORCID: https://orcid.org/0000-0002-3690-0321)
- Dusit Niyato (ORCID: https://orcid.org/0000-0002-7442-7416)
Institutions
- The University of Sydney (AU)
- Nanyang Technological University (SG)
- UNSW Sydney (AU)
- Health Sciences and Nutrition (AU)
- City University of Macau (MO)
Publication Details
- Journal
- Computer
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1109/mc.2024.3405397
- Citations
- 16
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 37.21