Information Exchange on 2WMH QA
76.7F1 ScoreOPTIMA-iSFT-DPO SC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OPTIMA-iSFT-DPO SCoptimization_strategy=iSFT-DPO, self_consistency=true2024.10 | 76.7 | 1,096 | |
| DITS-iSFT-DPO2025.02 | 76 | — | |
| OPTIMA-iSFT-DPOoptimization_strategy=iSFT-DPO2024.10 | 74.2 | 54.9 | |
| Optima-iSFT-DPO2025.02 | 74.2 | — | |
| OPTIMA-iSFT SCoptimization_strategy=iSFT, self_consistency=true2024.10 | 72.6 | 245.6 | |
| OPTIMA-iSFToptimization_strategy=iSFT2024.10 | 72.4 | 61.2 | |
| Optima-iSFT2025.02 | 72.4 | — | |
| OPTIMA-iDPO SCoptimization_strategy=iDPO, self_consistency=true2024.10 | 67.2 | 1,056.2 | |
| OPTIMA-iDPOoptimization_strategy=iDPO2024.10 | 66.1 | 35.9 | |
| Optima-iDPO2025.02 | 66.1 | — | |
| SCn=82024.10 | 28.7 | 1,052.8 | |
| MAD2024.10 | 25.9 | 543.7 | |
| MAD2025.02 | 25.9 | — | |
| AutoForm2024.10 | 24.7 | 117.7 | |
| AutoForm2025.02 | 24.7 | — | |
| CoT2024.10 | 20.5 | 139.8 | |
| CoT2025.02 | 20.5 | — |