大型語言模型知識編輯的全面研究

A Comprehensive Study of Knowledge Editing for Large Language Models

January 2, 2024

作者: Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, Siyuan Cheng, Ziwen Xu, Xin Xu, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen

cs.AI

摘要

大型語言模型（LLMs）展現出非凡的能力，能夠理解並生成與人類溝通密切相似的文本。然而，其主要限制在於訓練過程中對計算資源的巨大需求，這源於其龐大的參數化。這個挑戰進一步受到世界動態性的加劇，需要對LLMs進行頻繁更新，以修正過時信息或整合新知識，從而確保其持續相關性。許多應用需要在訓練後持續調整模型以解決缺陷或不良行為。對於即時模型修改，人們對高效輕量級方法越來越感興趣。近年來，知識編輯技術蓬勃發展，旨在有效修改LLMs在特定領域內的行為，同時保持其在各種輸入上的整體性能。本文首先定義知識編輯問題，然後全面評估最新方法。我們從教育和認知研究理論中汲取靈感，提出一個統一的分類標準，將知識編輯方法分為三組：利用外部知識、將知識合併到模型中，以及編輯內在知識。此外，我們引入一個新的基準，KnowEdit，用於對代表性知識編輯方法進行全面實證評估。此外，我們對知識定位進行了深入分析，這可以更深入地理解LLMs內在的知識結構。最後，我們討論了知識編輯的幾個潛在應用，概述了其廣泛而深遠的影響。

English

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization. This challenge is further intensified by the dynamic nature of the world, necessitating frequent updates to LLMs to correct outdated information or integrate new knowledge, thereby ensuring their continued relevance. Note that many applications demand continual model adjustments post-training to address deficiencies or undesirable behaviors. There is an increasing interest in efficient, lightweight methods for on-the-fly model modifications. To this end, recent years have seen a burgeoning in the techniques of knowledge editing for LLMs, which aim to efficiently modify LLMs' behaviors within specific domains while preserving overall performance across various inputs. In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches. Drawing inspiration from educational and cognitive research theories, we propose a unified categorization criterion that classifies knowledge editing methods into three groups: resorting to external knowledge, merging knowledge into the model, and editing intrinsic knowledge. Furthermore, we introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches. Additionally, we provide an in-depth analysis of knowledge location, which can provide a deeper understanding of the knowledge structures inherent within LLMs. Finally, we discuss several potential applications of knowledge editing, outlining its broad and impactful implications.