SOURCE-LINKED INTELLIGENCE

When Successful Knowledge Graph Edits Displace Correct Answers: Rank-Level Locality beyond Parameter Support

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Editing a knowledge graph embedding (KGE) model to promote a desired answer can displace correct answers from the returned list. Locality tests based only on facts that reuse the edited parameter can miss this ranking effect. We introduce a common rank-displacement audit at three scopes: facts supported by the edited parameter, other correct answers to the target query, and correct answers across queries with the same relation. We also derive dimensional and geometric conditions for an update to improve the target while exactly preserving selected scores. On FB15k-237 with DistMult and ComplEx

Read original source ↗ Open in workspace

recordType

paper

region

Global