Cross-Sectional Evaluation of Medical Disinformation Safeguards in Consumer-Facing Large Language Model Platforms

Natansh D. Modi; Cyril A. Alex; Abdulhalim A. Awaty; Bradley D. Menz; S. Bacchi; Kacper Gradoń; Jessica M. Logan; Andrew Rowland; Lisa Kalisch Ellett; Ross A. McKinnon; Michael D. Wiese; Michael J. Sorich; Ashley M Hopkins

doi:10.2196/89831

April 20, 2026JMIR InfodemiologyOpen Access

Cross-Sectional Evaluation of Medical Disinformation Safeguards in Consumer-Facing Large Language Model Platforms

View Full Paper

Ask AI

Bookmark

Share

Key Points

The aim is to assess how well different large language model platforms prevent the spread of health disinformation.
Conducted a cross-sectional analysis of six consumer-facing large language model platforms.
Evaluated the performance of these platforms against health-related disinformation using various prompt types.
Claude and ChatGPT demonstrated complete resistance to generating health disinformation.
Copilot, Meta AI, Grok, and Gemini showed significant vulnerabilities, allowing for health disinformation generation.

Implication

Cross-sectional evaluation shows varied safeguard effectiveness against health disinformation in AI platforms, indicating areas for improvement.

Abstract

This cross-sectional evaluation of six consumer-facing large language model platforms found significant heterogeneity in safeguard performance against the generation of health disinformation, with Claude and ChatGPT demonstrating complete resistance across all prompt types, while Copilot, Meta AI, Grok, and Gemini exhibited substantial vulnerabilities.

Cross-Sectional Evaluation of Medical Disinformation Safeguards in Consumer-Facing Large Language Model Platforms

Key Points

Implication

Abstract

Discussion

Cite This Study

Cross-Sectional Evaluation of Medical Disinformation Safeguards in Consumer-Facing Large Language Model Platforms

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading