Context-Aware Question Answering on TriState-Bench Sagr
94.25EM ScoreGreedy_no_ctx
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Greedy_no_ctxModel=Llama2-13B2026.06 | 94.25 | 96.5 | |
| Simple InterpModel=Llama2-13B, tau=0.252026.06 | 94.25 | 96.08 | |
| Simple InterpModel=Llama2-13B, tau=0.752026.06 | 94 | 95.99 | |
| GreedyModel=Llama2-13B2026.06 | 93.75 | 95.83 | |
| Simple InterpModel=Llama2-13B, tau=0.52026.06 | 93.75 | 95.81 | |
| ARRModel=Llama2-13B2026.06 | 93.75 | 95.81 | |
| AdaCADModel=Llama2-13B2026.06 | 93.25 | 95.4 | |
| Simple InterpBackbone=Llama3-8B, tau=0.252026.06 | 92.5 | 95.02 | |
| CADModel=Llama2-13B, alpha=0.252026.06 | 92 | 94.61 | |
| Greedy_no_ctxBackbone=Llama3-8B2026.06 | 91 | 93.65 | |
| GreedyModel=Llama3-8B-Inst2026.06 | 89.75 | 93.82 | |
| Simple InterpBackbone=Llama3-8B, tau=0.52026.06 | 89.25 | 92.59 | |
| ARRModel=Llama3-8B-Inst2026.06 | 89 | 93.77 | |
| AdaCADModel=Llama3-8B-Inst2026.06 | 88.5 | 93.22 | |
| ARRModel=Qwen2.5-7B2026.06 | 88.25 | 92.27 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.752026.06 | 87 | 91.23 | |
| GreedyModel=Qwen2.5-7B2026.06 | 86 | 90.76 | |
| COIECDModel=Llama3-8B-Inst2026.06 | 85.75 | 91.66 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.52026.06 | 85.5 | 90.47 | |
| CADModel=Llama2-13B, alpha=0.52026.06 | 85.5 | 89.46 | |
| CoCoAModel=Llama2-13B2026.06 | 85.5 | 89.46 | |
| COIECDModel=Llama2-13B2026.06 | 84 | 88.25 | |
| CADBackbone=Mistral-7B, alpha=0.252026.06 | 83.75 | 87.95 | |
| CoCoAModel=Llama3-8B-Inst2026.06 | 83.25 | 90.7 | |
| AdaCADBackbone=Mistral-7B2026.06 | 83.25 | 87.95 | |
| GreedyBackbone=Mistral-7B2026.06 | 82.75 | 87.76 | |
| AdaCADModel=Qwen2.5-7B2026.06 | 82.25 | 88.56 | |
| ARRBackbone=Mistral-7B2026.06 | 82 | 87.46 | |
| Simple InterpBackbone=Llama3-8B, tau=0.752026.06 | 81.75 | 87.01 | |
| Simple InterpModel=Qwen2.5-7B, tau=0.252026.06 | 81.25 | 86.92 | |
| Simple InterpBackbone=Mistral-7B, tau=0.752026.06 | 80.75 | 86.45 | |
| GreedyModel=Mistral-7B-Inst2026.06 | 80 | 87.12 | |
| ARRModel=Mistral-7B-Inst2026.06 | 79.75 | 87.3 | |
| Simple InterpBackbone=Mistral-7B, tau=0.52026.06 | 79.75 | 85.99 | |
| AdaCADModel=Mistral-7B-Inst2026.06 | 79.25 | 86.82 | |
| CADModel=Llama2-13B, alpha=0.752026.06 | 78 | 84.33 | |
| ARRBackbone=Llama3-8B2026.06 | 76.75 | 83.15 | |
| Simple InterpBackbone=Mistral-7B, tau=0.252026.06 | 75.5 | 83.36 | |
| COIECDModel=Llama2-13B-Inst2026.06 | 74.5 | 83.1 | |
| Greedy_no_ctxModel=Qwen2.5-7B2026.06 | 74.25 | 81.73 | |
| CADModel=Qwen2.5-7B, alpha=0.252026.06 | 73.5 | 83.45 | |
| CADBackbone=Mistral-7B, alpha=0.52026.06 | 73.25 | 75.91 | |
| GreedyModel=Llama2-13B-Inst2026.06 | 73 | 82.6 | |
| COIECDBackbone=Mistral-7B2026.06 | 72.75 | 75.56 | |
| CADModel=Llama2-13B, alpha=1.02026.06 | 72.5 | 80.35 | |
| COIECDModel=Mistral-7B-Inst2026.06 | 72.25 | 81.68 | |
| Greedy_no_ctxBackbone=Mistral-7B2026.06 | 71.75 | 81.1 | |
| AdaCADModel=Llama2-13B-Inst2026.06 | 71.5 | 81.7 | |
| GreedyBackbone=Llama3-8B2026.06 | 64.75 | 73.92 | |
| ARRModel=Llama2-13B-Inst2026.06 | 62.3 | 74.8 | |
| CADModel=Qwen2.5-7B, alpha=0.52026.06 | 60.25 | 74.26 | |
| CADModel=Mistral-7B-Inst2026.06 | 59.25 | 70.9 | |
| COIECDModel=Qwen2.5-7B2026.06 | 56.75 | 71.96 | |
| CADModel=Llama3-8B-Inst2026.06 | 53.25 | 65.57 | |
| CADModel=Qwen2.5-7B, alpha=0.752026.06 | 49.25 | 67.73 | |
| AdaCADBackbone=Llama3-8B2026.06 | 48.5 | 60.43 | |
| CADBackbone=Mistral-7B, alpha=0.752026.06 | 47 | 49.14 | |
| CADBackbone=Llama3-8B, alpha=0.252026.06 | 41.5 | 54.62 | |
| CADModel=Qwen2.5-7B, alpha=1.02026.06 | 36.25 | 56.18 | |
| COIECDBackbone=Llama3-8B2026.06 | 35 | 50.99 | |
| CoCoABackbone=Mistral-7B2026.06 | 32 | 48.19 | |
| CoCoAModel=Qwen2.5-7B2026.06 | 30.75 | 50.6 | |
| CADBackbone=Llama3-8B, alpha=0.52026.06 | 30.5 | 45.96 | |
| CoCoABackbone=Llama3-8B2026.06 | 30 | 45.52 | |
| CADModel=Llama2-13B-Inst2026.06 | 25.2 | 54.6 | |
| CADBackbone=Mistral-7B, alpha=1.02026.06 | 25 | 27.51 | |
| CADBackbone=Llama3-8B, alpha=0.752026.06 | 24.5 | 40.49 | |
| CADBackbone=Llama3-8B, alpha=1.02026.06 | 21.25 | 37.92 | |
| CoCoAModel=Llama2-13B-Inst2026.06 | 11 | 46.5 | |
| COIECDModel=Qwen2.5-7B-Inst2026.06 | 4.75 | 26.24 | |
| AdaCADModel=Qwen2.5-7B-Inst2026.06 | 4.25 | 25.36 | |
| GreedyModel=Qwen2.5-7B-Inst2026.06 | 2.5 | 27.49 | |
| CADModel=Qwen2.5-7B-Inst2026.06 | 2 | 20.07 | |
| CoCoAModel=Qwen2.5-7B-Inst2026.06 | 2 | 21.78 | |
| ARRModel=Qwen2.5-7B-Inst2026.06 | 1.75 | 26.24 | |
| CoCoAModel=Mistral-7B-Inst2026.06 | 0.25 | 24.16 |