Recent advancements in deep learning have precipitated the emergence of large language models (LLMs) which exhibit an impressive aptitude for understanding and producing text akin to human language. Despite the ability to train highly capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To that end, the past few years have witnessed a surge in techniques for editing LLMs, the objective of which is to alter the behavior of LLMs within a specific domain without negatively impacting performance across other inputs. This paper embarks on a deep exploration of the problems, methods, and opportunities relating to model editing for LLMs. In particular, we provide an exhaustive overview of the task definition and challenges associated with model editing, along with an in-depth empirical analysis of the most progressive methods currently at our disposal. We also build a new benchmark dataset to facilitate a more robust evaluation and pinpoint enduring issues intrinsic to existing techniques. Our objective is to provide valuable insights into the effectiveness and feasibility of each model editing technique, thereby assisting the research community in making informed decisions when choosing the most appropriate method for a specific task or context. Code and datasets will be available at https://github.com/zjunlp/EasyEdit.

翻译：近年来深度学习的重大进展催生了大语言模型（LLMs）的涌现，这些模型在类人语言理解与生成方面展现出卓越能力。尽管能够训练出高性能的大语言模型，但保持其时效性并修正错误的方法仍具挑战性。为此，过去几年涌现出大量大语言模型编辑技术，其目标是在特定领域内改变模型行为，同时不影响其他输入的表现。本文深入探索了大语言模型编辑面临的问题、方法与机遇。具体而言，我们系统梳理了模型编辑的任务定义与挑战，并对当前最先进的编辑方法进行了深入的实证分析。同时构建了新的基准数据集以促进更稳健的评估，并指出现有技术中存在的固有问题。本研究旨在为每种模型编辑技术的有效性和可行性提供宝贵见解，从而帮助研究社区在为特定任务或场景选择最合适方法时做出明智决策。相关代码和数据集将发布于 https://github.com/zjunlp/EasyEdit。