Long-form Medical Question Answering on Adversarial questions General
74.6Consensus SupportMed-PaLM 2
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Med-PaLM 2Evaluator=Physician raters, Independent evaluation=true2023.05 | 74.6 | 81.9 | 89.7 | 94.8 | 97 | 96.6 | 94.8 | 84.1 | 97 | 84.5 | 81 | 97.4 | 0.001 | |
| Med-PaLMEvaluator=Physician raters, Independent evaluation=true2023.05 | 57.8 | 68.5 | 81 | 87.5 | 83.2 | 81.9 | 85.8 | 69 | 80.2 | 67.2 | 65.5 | 88.8 | — |