Constraint Following on ComplexInstruct & CoDI (Level 1)
95.2ISRDVR_WS
Evaluation Results
| Method | Links | |
|---|---|---|
| DVR_WSBackbone=Llama-3.1-8B-Instruct, Refinement Repository=warm-start2024.10 | 95.2 | |
| DVR_CSBackbone=Llama-3.1-8B-Instruct, Refinement Repository=cold-start2024.10 | 94.5 | |
| ReActBackbone=Llama-3.1-8B-Instruct2024.10 | 94.2 | |
| CRITICBackbone=Llama-3.1-8B-Instruct2024.10 | 93.8 | |
| R-SampleBackbone=Llama-3.1-8B-Instruct2024.10 | 92.1 | |
| ReflxionBackbone=Llama-3.1-8B-Instruct2024.10 | 91.6 | |
| U-SCBackbone=Llama-3.1-8B-Instruct2024.10 | 90.9 | |
| VanillaBackbone=Llama-3.1-8B-Instruct2024.10 | 90.5 | |
| BSMBackbone=Llama-3.1-8B-Instruct2024.10 | 90.1 |