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

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.