Information Exchange on HotpotQA
0.574F1 ScoreOPTIMA-iSFT-DPO SC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OPTIMA-iSFT-DPO SCoptimization_strategy=iSFT-DPO, self_consistency=true2024.10 | 0.574 | 957.9 | |
| DITS-iSFT-DPO2025.02 | 0.572 | — | |
| OPTIMA-iSFT-DPOoptimization_strategy=iSFT-DPO2024.10 | 0.556 | 63.3 | |
| Optima-iSFT-DPO2025.02 | 0.556 | — | |
| OPTIMA-iSFT SCoptimization_strategy=iSFT, self_consistency=true2024.10 | 0.548 | 806.2 | |
| OPTIMA-iSFToptimization_strategy=iSFT2024.10 | 0.545 | 67.6 | |
| Optima-iSFT2025.02 | 0.545 | — | |
| OPTIMA-iDPO SCoptimization_strategy=iDPO, self_consistency=true2024.10 | 0.528 | 412.8 | |
| OPTIMA-iDPOoptimization_strategy=iDPO2024.10 | 0.525 | 45.7 | |
| Optima-iDPO2025.02 | 0.525 | — | |
| SCn=82024.10 | 0.338 | 996.3 | |
| MAD2024.10 | 0.284 | 570.9 | |
| MAD2025.02 | 0.284 | — | |
| AutoForm2024.10 | 0.282 | 97.7 | |
| AutoForm2025.02 | 0.282 | — | |
| CoT2024.10 | 0.256 | 123.7 | |
| CoT2025.02 | 0.256 | — |