Multi-label classification on Medical (F-Measure)
76.6Micro F1-ScoreAK
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AKModel=GPT-4o, Graph-free=true2026.05 | 76.6 | — | |
| AKSModel=GPT-4o, Graph-free=true2026.05 | 73.6 | — | |
| AOSModel=GPT-4o, Graph-free=true2026.05 | 71.9 | — | |
| AOModel=GPT-4o, Graph-free=true2026.05 | 71.4 | — | |
| AKModel=LLaMA 3.3-70B, Graph-free=true, Protocol=Zero-shot2026.05 | 70.2 | — | |
| AKSModel=LLaMA 3.3-70B, Graph-free=true, Protocol=Zero-shot with Self-Consistency2026.05 | 69.9 | — | |
| AOSModel=LLaMA 3.3-70B, Graph-free=true, Protocol=Zero-shot with Self-Consistency2026.05 | 67.8 | — | |
| AOModel=LLaMA 3.3-70B, Graph-free=true, Protocol=Zero-shot2026.05 | 66.9 | — | |
| BaselineSource=Sarkar et al., 20232026.05 | 59.4 | — | |
| AKModel=DS-R1 1.5B, Graph-free=true2026.05 | 49.7 | — | |
| AOModel=DS-R1 1.5B, Graph-free=true2026.05 | 48.8 | — | |
| DTECCFusion scheme=DTECC2026.03 | — | 4.83 | |
| MEECCFusion scheme=MEECC2026.03 | — | 40.72 | |
| MVECCFusion scheme=MVECC2026.03 | — | 40.94 | |
| STACKECCFusion scheme=STACKECC2026.03 | — | 8.38 | |
| UDDTECCFusion scheme=UDDTECC2026.03 | — | 6.45 |