Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.09855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909900344393728 |
|---|---|
| author | Kang, James Jin Bui, Dang Pham, Thanh Ling, Huo-Chong |
| author_facet | Kang, James Jin Bui, Dang Pham, Thanh Ling, Huo-Chong |
| contents | The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that sensitive information can be permanently removed once it has been used. Retraining from the beginning is prohibitively costly, and existing unlearning methods remain fragmented, difficult to verify, and often vulnerable to recovery. This paper surveys recent research on machine unlearning for LLMs and considers how far current approaches can address these challenges. We review methods for evaluating whether forgetting has occurred, the resilience of unlearned models against adversarial attacks, and mechanisms that can support user trust when model complexity or proprietary limits restrict transparency. Technical solutions such as differential privacy, homomorphic encryption, federated learning, and ephemeral memory are examined alongside institutional safeguards including auditing practices and regulatory frameworks. The review finds steady progress, but robust and verifiable unlearning is still unresolved. Efficient techniques that avoid costly retraining, stronger defenses against adversarial recovery, and governance structures that reinforce accountability are needed if LLMs are to be deployed safely in sensitive applications. By integrating technical and organizational perspectives, this study outlines a pathway toward AI systems that can be required to forget, while maintaining both privacy and public trust. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09855 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting Kang, James Jin Bui, Dang Pham, Thanh Ling, Huo-Chong Machine Learning The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that sensitive information can be permanently removed once it has been used. Retraining from the beginning is prohibitively costly, and existing unlearning methods remain fragmented, difficult to verify, and often vulnerable to recovery. This paper surveys recent research on machine unlearning for LLMs and considers how far current approaches can address these challenges. We review methods for evaluating whether forgetting has occurred, the resilience of unlearned models against adversarial attacks, and mechanisms that can support user trust when model complexity or proprietary limits restrict transparency. Technical solutions such as differential privacy, homomorphic encryption, federated learning, and ephemeral memory are examined alongside institutional safeguards including auditing practices and regulatory frameworks. The review finds steady progress, but robust and verifiable unlearning is still unresolved. Efficient techniques that avoid costly retraining, stronger defenses against adversarial recovery, and governance structures that reinforce accountability are needed if LLMs are to be deployed safely in sensitive applications. By integrating technical and organizational perspectives, this study outlines a pathway toward AI systems that can be required to forget, while maintaining both privacy and public trust. |
| title | Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.09855 |