# Fact-Checking Generative AI: Ontology-Driven Biological Graphs for Disease-Gene Link Verification

arXiv: https://arxiv.org/abs/2308.03929 · HTML: https://mlsanity.com/paper/2308.03929/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 27 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 1 of 1)

- [ProjE: Embedding Projection for Knowledge Graph Completion](https://mlsanity.com/paper/1611.05425/) (2016)

## Built on by (most cited first, 3 of 3)

- [From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT](https://mlsanity.com/paper/2502.14714/) (2025)
- [Can LLMs Support Medical Knowledge Imputation? An Evaluation-Based Perspective](https://mlsanity.com/paper/2503.22954/) (2025)
- [Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow](https://mlsanity.com/paper/2605.30400/) (2026)

## Abstract (arXiv)

Since the launch of various generative AI tools, scientists have been striving to evaluate their capabilities and contents, in the hope of establishing trust in their generative abilities. Regulations and guidelines are emerging to verify generated contents and identify novel uses. we aspire to demonstrate how ChatGPT claims are checked computationally using the rigor of network models. We aim to achieve fact-checking of the knowledge embedded in biological graphs that were contrived from ChatGPT contents at the aggregate level. We adopted a biological networks approach that enables the systematic interrogation of ChatGPT's linked entities. We designed an ontology-driven fact-checking algorithm that compares biological graphs constructed from approximately 200,000 PubMed abstracts with counterparts constructed from a dataset generated using the ChatGPT-3.5 Turbo model. In 10-samples of 250 randomly selected records a ChatGPT dataset of 1000 "simulated" articles , the fact-checking link accuracy ranged from 70% to 86%. This study demonstrated high accuracy of aggregate disease-gene links relationships found in ChatGPT-generated texts.