遗忘的必要性：通过工程化遗忘保障可信且负责任的大型语言模型安全
Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
AI总结：
针对大型语言模型无法可靠永久遗忘敏感信息的问题，本文综述其机器遗忘研究，分析现有方法的挑战与进展，从技术与制度层面勾勒保障隐私和信任的路径。
摘要：
大型语言模型在敏感领域的应用日益广泛，暴露出一个关键弱点：无法确保私有信息可被永久遗忘。然而，这些系统仍缺乏可靠机制，无法保证敏感信息一旦被使用后能被永久移除。从头开始重新训练成本过高，现有遗忘方法则较为零散、难以验证且常易被恢复。本文综述了大型语言模型机器遗忘的近期研究，探讨当前方法能在多大程度上应对这些挑战。我们回顾了评估遗忘是否发生的方法、已遗忘模型对抗攻击的韧性，以及在模型复杂性或专有性限制透明度时支持用户信任的机制。同时研究了差分隐私、同态加密、联邦学习和临时记忆等技术方案，以及审计实践和监管框架等制度保障。综述发现虽有稳步进展，但稳健且可验证的遗忘仍未解决。若要在敏感应用中安全部署大型语言模型，需避免高昂重新训练的高效技术、更强的对抗恢复防御，以及强化问责制的治理结构。本研究通过整合技术与组织视角，勾勒出AI系统既能按要求遗忘，又能维护隐私与公众信任的路径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
