LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

TL;DR

LyapLock is a novel model editing framework for large language models that ensures long-term knowledge preservation and improves sequential editing performance using Lyapunov optimization, scaling to over 10,000 edits.

Contribution

It introduces the first theoretically guaranteed model editing framework that balances knowledge updates with preservation over long sequences of edits.

Findings

Scales to over 10,000 sequential edits.

Boosts editing efficacy by 11.89% over SOTA.

Stabilizes general capabilities during editing.

Abstract

Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locate-then-edit approaches exhibit a progressive performance decline during sequential editing, due to inadequate mechanisms for long-term knowledge preservation. To tackle this, we model the sequential editing as a constrained stochastic programming. Given the challenges posed by the cumulative preservation error constraint and the gradually revealed editing tasks, \textbf{LyapLock} is proposed. It integrates queuing theory and Lyapunov optimization to decompose the long-term constrained programming into tractable stepwise subproblems for efficient solving. This is the first model editing framework with rigorous theoretical guarantees, achieving asymptotic optimal editing performance while meeting the constraints of long-term knowledge preservation. Experimental results show that our framework scales sequential editing capacity to over 10,000 edits while stabilizing general capabilities and boosting average editing efficacy by 11.89\% over SOTA baselines. Furthermore, it can be leveraged to enhance the performance of baseline methods. Our code is released on https://github.com/caskcsg/LyapLock.