List your company

Context-Aware Question Answering on TriState-Bench Sagr

94.25EM ScoreGreedy_no_ctx
-3.5121.8747.2572.63Jun 9, 2026

Evaluation results

MethodLinks
Greedy_no_ctxModel=Llama2-13B2026.0694.2596.5
Simple InterpModel=Llama2-13B, tau=0.252026.0694.2596.08
Simple InterpModel=Llama2-13B, tau=0.752026.069495.99
GreedyModel=Llama2-13B2026.0693.7595.83
Simple InterpModel=Llama2-13B, tau=0.52026.0693.7595.81
ARRModel=Llama2-13B2026.0693.7595.81
AdaCADModel=Llama2-13B2026.0693.2595.4
Simple InterpBackbone=Llama3-8B, tau=0.252026.0692.595.02
CADModel=Llama2-13B, alpha=0.252026.069294.61
Greedy_no_ctxBackbone=Llama3-8B2026.069193.65
GreedyModel=Llama3-8B-Inst2026.0689.7593.82
Simple InterpBackbone=Llama3-8B, tau=0.52026.0689.2592.59
ARRModel=Llama3-8B-Inst2026.068993.77
AdaCADModel=Llama3-8B-Inst2026.0688.593.22
ARRModel=Qwen2.5-7B2026.0688.2592.27
Simple InterpModel=Qwen2.5-7B, tau=0.752026.068791.23
GreedyModel=Qwen2.5-7B2026.068690.76
COIECDModel=Llama3-8B-Inst2026.0685.7591.66
Simple InterpModel=Qwen2.5-7B, tau=0.52026.0685.590.47
CADModel=Llama2-13B, alpha=0.52026.0685.589.46
CoCoAModel=Llama2-13B2026.0685.589.46
COIECDModel=Llama2-13B2026.068488.25
CADBackbone=Mistral-7B, alpha=0.252026.0683.7587.95
CoCoAModel=Llama3-8B-Inst2026.0683.2590.7
AdaCADBackbone=Mistral-7B2026.0683.2587.95
GreedyBackbone=Mistral-7B2026.0682.7587.76
AdaCADModel=Qwen2.5-7B2026.0682.2588.56
ARRBackbone=Mistral-7B2026.068287.46
Simple InterpBackbone=Llama3-8B, tau=0.752026.0681.7587.01
Simple InterpModel=Qwen2.5-7B, tau=0.252026.0681.2586.92
Simple InterpBackbone=Mistral-7B, tau=0.752026.0680.7586.45
GreedyModel=Mistral-7B-Inst2026.068087.12
ARRModel=Mistral-7B-Inst2026.0679.7587.3
Simple InterpBackbone=Mistral-7B, tau=0.52026.0679.7585.99
AdaCADModel=Mistral-7B-Inst2026.0679.2586.82
CADModel=Llama2-13B, alpha=0.752026.067884.33
ARRBackbone=Llama3-8B2026.0676.7583.15
Simple InterpBackbone=Mistral-7B, tau=0.252026.0675.583.36
COIECDModel=Llama2-13B-Inst2026.0674.583.1
Greedy_no_ctxModel=Qwen2.5-7B2026.0674.2581.73
CADModel=Qwen2.5-7B, alpha=0.252026.0673.583.45
CADBackbone=Mistral-7B, alpha=0.52026.0673.2575.91
GreedyModel=Llama2-13B-Inst2026.067382.6
COIECDBackbone=Mistral-7B2026.0672.7575.56
CADModel=Llama2-13B, alpha=1.02026.0672.580.35
COIECDModel=Mistral-7B-Inst2026.0672.2581.68
Greedy_no_ctxBackbone=Mistral-7B2026.0671.7581.1
AdaCADModel=Llama2-13B-Inst2026.0671.581.7
GreedyBackbone=Llama3-8B2026.0664.7573.92
ARRModel=Llama2-13B-Inst2026.0662.374.8
CADModel=Qwen2.5-7B, alpha=0.52026.0660.2574.26
CADModel=Mistral-7B-Inst2026.0659.2570.9
COIECDModel=Qwen2.5-7B2026.0656.7571.96
CADModel=Llama3-8B-Inst2026.0653.2565.57
CADModel=Qwen2.5-7B, alpha=0.752026.0649.2567.73
AdaCADBackbone=Llama3-8B2026.0648.560.43
CADBackbone=Mistral-7B, alpha=0.752026.064749.14
CADBackbone=Llama3-8B, alpha=0.252026.0641.554.62
CADModel=Qwen2.5-7B, alpha=1.02026.0636.2556.18
COIECDBackbone=Llama3-8B2026.063550.99
CoCoABackbone=Mistral-7B2026.063248.19
CoCoAModel=Qwen2.5-7B2026.0630.7550.6
CADBackbone=Llama3-8B, alpha=0.52026.0630.545.96
CoCoABackbone=Llama3-8B2026.063045.52
CADModel=Llama2-13B-Inst2026.0625.254.6
CADBackbone=Mistral-7B, alpha=1.02026.062527.51
CADBackbone=Llama3-8B, alpha=0.752026.0624.540.49
CADBackbone=Llama3-8B, alpha=1.02026.0621.2537.92
CoCoAModel=Llama2-13B-Inst2026.061146.5
COIECDModel=Qwen2.5-7B-Inst2026.064.7526.24
AdaCADModel=Qwen2.5-7B-Inst2026.064.2525.36
GreedyModel=Qwen2.5-7B-Inst2026.062.527.49
CADModel=Qwen2.5-7B-Inst2026.06220.07
CoCoAModel=Qwen2.5-7B-Inst2026.06221.78
ARRModel=Qwen2.5-7B-Inst2026.061.7526.24
CoCoAModel=Mistral-7B-Inst2026.060.2524.16