Question Answering on TriState
66.75EMARR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ARRModel=Llama3-8B-Inst2026.06 | 66.75 | 73.73 | |
| GreedyModel=Llama3-8B-Inst2026.06 | 61 | 66.96 | |
| ARRModel=Mistral-7B-Inst2026.06 | 60.92 | 69.57 | |
| AdaCADModel=Llama3-8B-Inst2026.06 | 60.17 | 66.41 | |
| COIECDModel=Llama3-8B-Inst2026.06 | 58.75 | 65.58 | |
| CoCoAModel=Llama3-8B-Inst2026.06 | 56.92 | 64.52 | |
| AdaCADModel=Mistral-7B-Inst2026.06 | 55.17 | 63.2 | |
| GreedyModel=Mistral-7B-Inst2026.06 | 54.5 | 62.81 | |
| COIECDModel=Mistral-7B-Inst2026.06 | 51.33 | 60.28 | |
| GreedyModel=Llama2-13B-Inst2026.06 | 50.17 | 58.93 | |
| AdaCADModel=Llama2-13B-Inst2026.06 | 50.07 | 58.93 | |
| COIECDModel=Llama2-13B-Inst2026.06 | 49.63 | 58.5 | |
| CADModel=Mistral-7B-Inst2026.06 | 44.92 | 54.92 | |
| ARRModel=Llama2-13B-Inst2026.06 | 44.17 | 57.07 | |
| CADModel=Llama3-8B-Inst2026.06 | 38.08 | 50.17 | |
| CADModel=Llama2-13B-Inst2026.06 | 25.13 | 43.6 | |
| CoCoAModel=Llama2-13B-Inst2026.06 | 7.5 | 37.27 | |
| CADModel=Qwen2.5-7B-Inst2026.06 | 2.83 | 17.77 | |
| COIECDModel=Qwen2.5-7B-Inst2026.06 | 2.42 | 19.48 | |
| AdaCADModel=Qwen2.5-7B-Inst2026.06 | 2.25 | 20.1 | |
| CoCoAModel=Qwen2.5-7B-Inst2026.06 | 1.5 | 18.45 | |
| GreedyModel=Qwen2.5-7B-Inst2026.06 | 1.25 | 21.01 | |
| ARRModel=Qwen2.5-7B-Inst2026.06 | 0.92 | 20.47 | |
| CoCoAModel=Mistral-7B-Inst2026.06 | 0.25 | 19.28 |