Medical Question Answering on Huatuo-26M Lite
66.38Win RateLLM-AutoDP
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=No-Process2026.01 | 66.38 | 1.74 | 31.88 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=No-Process2026.01 | 62.5 | 0.5 | 37 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=No-Process2026.01 | 61.25 | 2.25 | 36.5 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=RS2026.01 | 57.43 | 5 | 37.57 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=All-Process2026.01 | 57.24 | 4.75 | 38.01 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=SELA2026.01 | 57.24 | 4.75 | 38.01 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=RS2026.01 | 55.9 | 5 | 39.1 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=All-Process2026.01 | 54.18 | 3.25 | 42.57 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=SELA2026.01 | 54.18 | 3.25 | 42.57 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=All-Process2026.01 | 53.25 | 4.75 | 41.75 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=SELA2026.01 | 53.25 | 4.75 | 41.75 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=RS2026.01 | 51.5 | 5 | 43.5 |