Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Understand

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps.

• When such problems are identified, we want to make targeted edits while avoiding expensive retraining.
• However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits.
• We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs.