Long-form Medical Question Answering on Adversarial questions Health equity focused
78.4Consensus Support RateMed-PaLM 2
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Med-PaLM 2Evaluator=Physician raters, Independent evaluation=true2023.05 | 78.4 | 76.4 | 91.3 | 94.9 | 96.9 | 95.5 | 94.7 | 86.8 | 95.5 | 84.8 | 80.6 | 95.8 | 0 | |
| Med-PaLMEvaluator=Physician raters, Independent evaluation=true2023.05 | 59 | 57.6 | 78.4 | 86.8 | 82.3 | 80.6 | 85.4 | 72.2 | 79.5 | 63.8 | 58.7 | 86 | — |