SOURCE-LINKED INTELLIGENCE
When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance Weighting
Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interaction at a fixed model checkpoint by decomposing a localized gradient into edited and retained untouched components. Squared relative selection bias is a ratio of quadratics whose derivative has the sign of an explicit quadratic polynomial. Localization can increase, decrease, or nonmonotonically change this diagnostic; its direction depends on component biases and geometry. Oracle importance weighting recovers the population mean for each fixed lo
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-12T04:38:50.000Z
First collected: 2026-09-20T16:41:15.630Z. This is not the publication date.