AI RESEARCH
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
arXiv CS.CL
•
ArXi:2604.12559v1 Announce Type: new Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address this, we propose FABLE, a hierarchical framework that decouples fine-grained fact injection from holistic text generation. FABLE follows a two-stage, fact-first strategy: discrete facts are anchored in shallow layers, followed by minimal updates to deeper layers to produce coherent text.