We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.

翻译：我们探索了大型语言模型（LLM）领域的机器遗忘（MU），称为LLM遗忘。这一举措旨在消除不期望的数据影响（例如敏感或非法信息）及相关模型能力，同时保持必要知识生成的完整性，并且不影响因果无关的信息。我们设想LLM遗忘将成为LLM生命周期管理中的关键要素，可能作为开发不仅安全、可靠、可信赖，而且资源高效（无需完全重新训练）的生成式AI的重要基础。我们从前瞻性表述、方法论、度量指标和应用等方面探讨了LLM中的遗忘格局。特别是，我们强调了现有LLM遗忘研究中常被忽视的方面，例如遗忘范围、数据-模型交互以及多方面的效能评估。我们还建立了LLM遗忘与相关领域（如模型编辑、影响函数、模型解释、对抗训练和强化学习）之间的联系。此外，我们概述了一个有效的LLM遗忘评估框架，并探索了其在版权与隐私保护以及社会技术危害缓解中的应用。