Traceable LLM-based validation of statements in knowledge graphs

TL;DR

This paper introduces a traceable LLM-based method for validating RDF triples in knowledge graphs by leveraging external document retrieval, achieving high precision but requiring human oversight, and demonstrating potential for large-scale verification.

Contribution

The paper proposes a retrieval-augmented generation workflow that verifies knowledge graph statements without relying on internal LLM knowledge, enhancing traceability and applicability in biosciences.

Findings

Precision of 88% on BioRED dataset

Recall of 44% indicating need for human oversight

Effective on Wikidata for large-scale statement verification

Abstract

This article presents a method for verifying RDF triples using LLMs, with an emphasis on providing traceable arguments. Because the LLMs cannot currently reliably identify the origin of the information used to construct the response to the user prompt, our approach is to avoid using internal LLM factual knowledge altogether. Instead, verified RDF statements are compared to chunks of external documents retrieved through a web search or Wikipedia. To assess the possible application of this retrieval augmented generation (RAG) workflow on biosciences content, we evaluated 1,719 positive statements from the BioRED dataset and the same number of newly generated negative statements. The resulting precision is 88 %, and recall is 44 %. This indicates that the method requires human oversight. We also evaluated the method on the SNLI dataset, which allowed us to compare our approach with models specifically tuned for the natural language inference task. We demonstrate the method on Wikidata, where a SPARQL query is used to automatically retrieve statements needing verification. Overall, the results suggest that LLMs could be used for large-scale verification of statements in KGs, a task previously unfeasible due to human annotation costs.