AI RESEARCH
More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
arXiv CS.LG
•
ArXi:2605.11836v1 Announce Type: new Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabilities, yet it remains plagued by catastrophic forgetting and model collapse. Empirically, we find that recent editors resilient over long horizons share the same core strategy: Lifelong Normalization (LN), which normalizes value gradients using running statistics.