CoME: An Unlearning-based Approach to Conflict-free Model Editing

Understand

Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability.

• While model editing methods have been developed to address such errors without full re-training, they frequently suffer from knowledge conflicts, where outdated information interferes with new knowledge.
• In this work, we propose Conflict-free Model Editing (CoME), a novel framework that enhances the accuracy of knowledge updates in LLMs by selectively removing outdated knowledge.
• CoME leverages unlearning to mitigate knowledge interference, allowing new information to be integrated without compromising relevant linguistic features.