SOURCE-LINKED INTELLIGENCE

KLOD: Locality-Preserving Knowledge Editing via Non-Target Distribution Preservation

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Fine-tuning-based knowledge editing is simple and architecture-agnostic, but standard cross-entropy increases the edited target probability without explicitly constraining changes in the non-target output distribution. In sequential editing, such unconstrained redistribution can accumulate as distributional drift and contribute to locality degradation. We propose KLOD, a bounded and distribution-preserving objective for fine-tuning-based knowledge editing that separates the intended target update from distributions that should remain stable. KLOD stops target amplification once a probability t

Read original source ↗ Open in workspace

recordType

paper

region

Global