Long-form generation on 1D-DiffTask
0.24PRRSATMD-MSP
Evaluation Results
| Method | Links | |
|---|---|---|
| SATMD-MSPModel=Gemma-2-9B2026.04 | 0.24 | |
| SATMD-MSPModel=Llama 3.1-8B2026.04 | 0.22 | |
| SATRMD-MSPModel=Llama 3.1-8B2026.04 | 0.1 | |
| HUQ-SATRMDModel=Llama 3.1-8B2026.04 | 0.09 | |
| HUQ-SATMDModel=Llama 3.1-8B2026.04 | 0.07 | |
| SAPLMA (mid)Model=Llama 3.1-8B2026.04 | 0.07 | |
| HUQ-SATMDModel=Gemma-2-9B2026.04 | 0.07 | |
| SATRMD-MSPModel=Gemma-2-9B2026.04 | 0.03 | |
| SAPLMA (mid)Model=Gemma-2-9B2026.04 | 0.03 | |
| MSPModel=Llama 3.1-8B2026.04 | -0.01 | |
| HBOModel=Llama 3.1-8B2026.04 | -0.01 | |
| HUQ-SATRMDModel=Gemma-2-9B2026.04 | -0.08 | |
| MSPModel=Gemma-2-9B2026.04 | -0.1 | |
| HBOModel=Gemma-2-9B2026.04 | -0.1 |