SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.07507 · 2024

Traceable LLM-based validation of statements in knowledge graphs

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.07507")
get_code_for_paper("2409.07507")
have("2409.07507")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.07507.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.07507.svg)](https://syntology.ai/paper/2409.07507)

Connect an agent — have() is free.