Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models

TL;DR

This paper introduces UnKE, a novel method for editing unstructured knowledge in large language models, addressing limitations of previous techniques designed for structured data, and demonstrates superior performance on new and traditional datasets.

Contribution

UnKE extends knowledge editing to unstructured data by proposing non-local key-value storage and cause-driven token optimization, improving effectiveness and robustness.

Findings

UnKE outperforms existing methods on UnKEBench and structured datasets.

UnKE demonstrates robust batch and sequential editing capabilities.

UnKE effectively handles long-form, noisy, and complex unstructured knowledge.

Abstract

Recent knowledge editing methods have primarily focused on modifying structured knowledge in large language models. However, this task setting overlooks the fact that a significant portion of real-world knowledge is stored in an unstructured format, characterized by long-form content, noise, and a complex yet comprehensive nature. Techniques like "local layer key-value storage" and "term-driven optimization", as used in previous methods like MEMIT, are not effective for handling unstructured knowledge. To address these challenges, we propose a novel Unstructured Knowledge Editing method, namely UnKE, which extends previous assumptions in the layer dimension and token dimension. Firstly, in the layer dimension, we propose non-local block key-value storage to replace local layer key-value storage, increasing the representation ability of key-value pairs and incorporating attention layer knowledge. Secondly, in the token dimension, we replace "term-driven optimization" with "cause-driven optimization", which edits the last token directly while preserving context, avoiding the need to locate terms and preventing the loss of context information. Results on newly proposed unstructured knowledge editing dataset (UnKEBench) and traditional structured datasets demonstrate that UnKE achieves remarkable performance, surpassing strong baselines. In addition, UnKE has robust batch editing and sequential editing capabilities.