The Frontier of Data Erasure: Machine Unlearning for Large Language Models (2403.15779v1)
Abstract: LLMs are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information from their vast datasets. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns, offering techniques for LLMs to selectively discard certain data. This paper reviews the latest in machine unlearning for LLMs, introducing methods for the targeted forgetting of information to address privacy, ethical, and legal challenges without necessitating full model retraining. It divides existing research into unlearning from unstructured/textual data and structured/classification data, showcasing the effectiveness of these approaches in removing specific data while maintaining model efficacy. Highlighting the practicality of machine unlearning, this analysis also points out the hurdles in preserving model integrity, avoiding excessive or insufficient data removal, and ensuring consistent outputs, underlining the role of machine unlearning in advancing responsible, ethical AI.
- K. Singhal, S. Azizi, T. Tu, S. S. Mahdavi, J. Wei, H. W. Chung, N. Scales, A. Tanwani, H. Cole-Lewis, S. Pfohl et al., “Large language models encode clinical knowledge,” Nature, vol. 620, no. 7972, pp. 172–180, 2023.
- Y. Cao and J. Yang, “Towards making systems forget with machine unlearning,” in 2015 IEEE symposium on security and privacy. IEEE, 2015, pp. 463–480.
- D. Zhang, P. Finckenberg-Broman, T. Hoang, S. Pan, Z. Xing, M. Staples, and X. Xu, “Right to be forgotten in the era of large language models: Implications, challenges, and solutions,” arXiv preprint arXiv:2307.03941, 2023.
- J. Jang, D. Yoon, S. Yang, S. Cha, M. Lee, L. Logeswaran, and M. Seo, “Knowledge unlearning for mitigating privacy risks in language models,” arXiv preprint arXiv:2210.01504, 2022.
- R. Eldan and M. Russinovich, “Who’s harry potter? approximate unlearning in llms,” arXiv preprint arXiv:2310.02238, 2023.
- A. Karamolegkou, J. Li, L. Zhou, and A. Søgaard, “Copyright violations and large language models,” in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, pp. 7403–7412.
- M. Pawelczyk, S. Neel, and H. Lakkaraju, “In-context unlearning: Language models as few shot unlearners,” arXiv preprint arXiv:2310.07579, 2023.
- B. Min, H. Ross, E. Sulem, A. P. B. Veyseh, T. H. Nguyen, O. Sainz, E. Agirre, I. Heintz, and D. Roth, “Recent advances in natural language processing via large pre-trained language models: A survey,” ACM Computing Surveys, vol. 56, no. 2, pp. 1–40, 2023.
- X. Lu, S. Welleck, J. Hessel, L. Jiang, L. Qin, P. West, P. Ammanabrolu, and Y. Choi, “Quark: Controllable text generation with reinforced unlearning,” Advances in neural information processing systems, vol. 35, pp. 27 591–27 609, 2022.
- J. Chen and D. Yang, “Unlearn what you want to forget: Efficient unlearning for llms,” arXiv preprint arXiv:2310.20150, 2023.
- L. Wang, T. Chen, W. Yuan, X. Zeng, K.-F. Wong, and H. Yin, “Kga: A general machine unlearning framework based on knowledge gap alignment,” arXiv preprint arXiv:2305.06535, 2023.
- C. Yu, S. Jeoung, A. Kasi, P. Yu, and H. Ji, “Unlearning bias in language models by partitioning gradients,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 6032–6048.
- A. Kassem, O. Mahmoud, and S. Saad, “Preserving privacy through dememorization: An unlearning technique for mitigating memorization risks in language models,” in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, pp. 4360–4379.
- Y. Yao, X. Xu, and Y. Liu, “Large language model unlearning,” arXiv preprint arXiv:2310.10683, 2023.
- Z. Ma, Y. Liu, X. Liu, J. Liu, J. Ma, and K. Ren, “Learn to forget: Machine unlearning via neuron masking,” IEEE Transactions on Dependable and Secure Computing, 2022.
- Youyang Qu (15 papers)
- Ming Ding (219 papers)
- Nan Sun (19 papers)
- Kanchana Thilakarathna (28 papers)
- Tianqing Zhu (85 papers)
- Dusit Niyato (671 papers)