Medical Reasoning on XMEMRs
42.33RecallRE-MCDF
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| RE-MCDFBackbone=Qwen2.5-7B-Instruct2026.02 | 42.33 | 38.78 | 40.48 | |
| RE-MCDFBackbone=GLM-4-9B2026.02 | 42.23 | 38.69 | 40.38 | |
| Graph-CoTBackbone=Qwen2.5-7B-Instruct2026.02 | 40.64 | 37.06 | 38.76 | |
| ToTBackbone=GLM-4-9B2026.02 | 38.82 | 35.62 | 37.15 | |
| MedIKALBackbone=GLM-4-9B2026.02 | 38.77 | 37.91 | 38.34 | |
| MindMapBackbone=Qwen2.5-7B-Instruct2026.02 | 38.46 | 36.45 | 37.43 | |
| Graph-CoTBackbone=GLM-4-9B2026.02 | 38.45 | 37.87 | 38.16 | |
| MAGICBackbone=GLM-4-9B2026.02 | 38.3 | 35.17 | 36.67 | |
| MedIKALBackbone=Qwen2.5-7B-Instruct2026.02 | 38.24 | 38.32 | 38.28 | |
| Sc-CoTBackbone=GLM-4-9B2026.02 | 38.1 | 35 | 36.48 | |
| ICPBackbone=GLM-4-9B2026.02 | 38.1 | 34.86 | 36.41 | |
| KERAPBackbone=GLM-4-9B2026.02 | 37.88 | 36.7 | 37.28 | |
| CoTBackbone=GLM-4-9B2026.02 | 37.33 | 35.8 | 36.55 | |
| MindMapBackbone=GLM-4-9B2026.02 | 35.48 | 38.4 | 36.88 | |
| KG-RankBackbone=Qwen2.5-7B-Instruct2026.02 | 35.39 | 32.42 | 33.83 | |
| CoTBackbone=Qwen2.5-7B-Instruct2026.02 | 35.01 | 32.85 | 33.9 | |
| MAGICBackbone=Qwen2.5-7B-Instruct2026.02 | 34.88 | 33.26 | 34.05 | |
| KG-RankBackbone=GLM-4-9B2026.02 | 34.19 | 37.38 | 35.72 | |
| ICPBackbone=Qwen2.5-7B-Instruct2026.02 | 34.01 | 32.5 | 33.24 | |
| ToTBackbone=Qwen2.5-7B-Instruct2026.02 | 33.71 | 31.01 | 32.3 | |
| KERAPBackbone=Qwen2.5-7B-Instruct2026.02 | 33.14 | 37.1 | 35.01 | |
| Sc-CoTBackbone=Qwen2.5-7B-Instruct2026.02 | 31.03 | 34.62 | 32.73 |