Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
GraphEvalgithub.comGraphEval is a framework that evaluates large language model (LLM) factuality using large-scale knowledge graphs like DBpedia with over 10 million facts, eliminating the need for expensive human annotation. It employs a separate judge model to assess the correctness of LLM-generated answers, reducing evaluation costs while ensuring accuracy.
Parse Score
Sources
arxiv.org shapes more of what AI says about GraphEval than any other source, at 100% of its citations.
