Traceable LLM-based validation of statements in knowledge graphs
This addresses the challenge of traceable validation for knowledge graphs, particularly in biosciences, but is incremental as it builds on existing RAG methods.
The authors tackled the problem of verifying RDF triples in knowledge graphs using LLMs by avoiding reliance on internal LLM knowledge and instead comparing statements to external documents via a retrieval augmented generation workflow. They achieved a precision of 88% and recall of 44% on biosciences data, indicating the method requires human oversight but could enable large-scale verification previously unfeasible due to cost.
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.