measurement
GPT-4o exhibited the highest hallucination rates in Chronological Ordering (24.6%) and Lab Data Understanding (18.7%) compared to other models, with many of these hallucinations classified by medical experts as posing 'Significant' or 'Considerable' clinical risk.
Authors
Sources
- Medical Hallucination in Foundation Models and Their ... www.medrxiv.org via serper
- Medical Hallucination in Foundation Models and Their Impact on ... www.medrxiv.org via serper
Referenced by nodes (2)
- hallucination concept
- GPT-4 concept