Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

ArXi:2602.20207v2 Announce Type: replace-cross Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize knowledge at different depths of the model, resulting in different sample-wise editing performance for a fixed editing layer.