Medical Question Answering on MedMCQA translated (test)
43.2Accuracy (ZH)LoRAFlow
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| LoRAFlowBase LLM=LLaMA-3-8B, Paradigm=Supervised2025.12 | 43.2 | 39.3 | 43.5 | 42 | |
| Avg [0.5, 0.5]Base LLM=LLaMA-3-8B, Paradigm=Static fusion2025.12 | 42.4 | 40 | 34.7 | 39 | |
| qa-FLoRABase LLM=LLaMA-3-8B, Paradigm=Data & Training free2025.12 | 39.6 | 38 | 42.2 | 39.9 | |
| Centroid sim.Base LLM=LLaMA-3-8B, Paradigm=Training free2025.12 | 35.3 | 22.7 | 30.6 | 29.5 | |
| Centroid sim.Base LLM=LLaMA-2-7B, Paradigm=Training free2025.12 | 32.4 | 32.7 | 17 | 27.4 | |
| LoRAFlowBase LLM=LLaMA-2-7B, Paradigm=Supervised2025.12 | 31.7 | 35.3 | 30.6 | 32.5 | |
| LoRAHubBase LLM=LLaMA-2-7B, Paradigm=Supervised2025.12 | 30.5 | 33.2 | 26.7 | 30.1 | |
| qa-FLoRABase LLM=LLaMA-2-7B, Paradigm=Data & Training free2025.12 | 30 | 39 | 31 | 33.3 | |
| Avg [0.5, 0.5]Base LLM=LLaMA-2-7B, Paradigm=Static fusion2025.12 | 28 | 33 | 28 | 29.7 |