Long-form Medical Question Answering on Adversarial questions All (full)
76.9Consensus SupportMed-PaLM 2
Evaluation results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Med-PaLM 2Evaluator=Physician raters, Independent evaluation=true2023.05 | 76.9 | 78.6 | 90.6 | 94.9 | 96.9 | 95.9 | 94.7 | 85.7 | 96.1 | 84.7 | 80.8 | 96.4 | 0 | |
| Med-PaLMEvaluator=Physician raters, Independent evaluation=true2023.05 | 58.5 | 61.9 | 79.4 | 87.1 | 82.7 | 81.1 | 85.5 | 70.9 | 79.8 | 65.1 | 61.4 | 87.1 | — |