Knowledge graph repair improves by selectively retrieving external evidence
Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair
DatabasesArtificial Intelligence
Summary
Knowledge graphs store facts but can have errors or missing information that affects their usefulness. The authors created a method where a computer agent tries to fix these errors step-by-step and decides when to look up extra information from outside sources. Using this system, the agent learns when consulting outside knowledge helps or hurts fixing errors, which varies by situation. This approach uses less effort than always checking outside sources and usually fixes the graph better than never checking.
What this means in practice
- •For enterprise data engineers: Improve automatic correction of inconsistent business knowledge graphs by selectively querying external databases during repair.
- •For smart building automation teams: Enhance accuracy of building automation knowledge bases by controlling when to retrieve external evidence to resolve conflicting data.
Authors
Tung-Wei Lin, Gabe Fierro, Han Li, Tianzhen Hong, Pierluigi Nuzzo, Alberto Sangiovanni-Vinentelli
Abstract
Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph. External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful. We propose a framework for selective retrieval in iterative graph repair. An LLM repair agent explores and edits the graph, while a router controls its access to a researcher agent that retrieves external evidence. We extend a violation-injection framework to generate cases with multiple compatible violations and known reference repairs. The agent's repair outcomes on these cases provide supervision for training the deployment-specific router. On two building-automation datasets, researcher access improves repairs for some violations and degrades them for others, with effects differing across deployments. The router uses fewer repair-time tokens than always enabling access in all six evaluation suites. It achieves higher repair $F_1$ than always disabling access in five of six suites.