Evidence-Based Frameworks for Generative Artificial Intelligence

Thomas F. Heston^1,2
Email: theston@uw.edu (T.F.H.)
Manuscript received February 28, 2026; accepted March 10, 2026; published April 8, 2026.

Abstract—Generative artificial intelligence and large language models increasingly influence education, research, and decision support. However, current systems often prioritize narrative popularity over evidentiary strength, leading to information cascades and citation loops. This paper proposes a multidisciplinary framework for evaluating AI-generated claims based on the methodological discipline of evidence-based medicine. By integrating blockchain technology for evidence provenance and multi-agent audit protocols, generative systems can transition from narrative-based outputs to evidence-based syntheses. This approach ensures that information is weighted by methodological reliability rather than frequency of repetition, enhancing the trustworthiness of artificial intelligence in high-stakes environments.

Keywords—generative AI, evidence-based medicine, blockchain, decision science

Cite: Thomas F. Heston, "Evidence-Based Frameworks for Generative Artificial Intelligence," International Journal of Blockchain Technologies and Applications vol. 4, no. 1, pp. 34-38, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0)