K-Edit: Language Model Editing with Contextual Knowledge Awareness

TL;DR

K-Edit introduces a method for editing large language models that maintains contextual consistency using knowledge graphs, improving multi-hop question answering without sacrificing scalability.

Contribution

The paper presents K-Edit, a novel approach that incorporates knowledge graphs to generate contextually consistent edits in language models.

Findings

Significant improvements in multi-hop question answering.

Maintains scalability and effectiveness of model edits.

Ensures contextual consistency in knowledge updates.

Abstract

As the world changes, we need to be able to update our models and correct false information without costly retraining. Knowledge-based model editing enables precise modifications to the weights of large language models in order to modify the information encoded within. Recent approaches have seen success in enabling recall of edited information for thousands of edits at once. However, these approaches fail to produce edits that account for associated contextual information. We present K-Edit, an effective approach to generating contextually consistent knowledge edits. By using knowledge graphs, which maintain contextual consistency when an edge is edited, we are able to generate additional \textit{contextual edits} that ensure consistency of related information in the language model. Our experiments demonstrate significant improvements in multi-hop question answering while maintaining the general effectiveness and scalability of model edits.