List your company

Context-Aware Question Answering on TriState-Bench Sres

94.25EMGreedy_no_ctx
-3.7721.677547.12572.5725Jun 9, 2026

Evaluation results

MethodLinks
Greedy_no_ctxModel=Llama2-13B2026.0694.2596.5
Greedy_no_ctxBackbone=Llama3-8B2026.0691.594
Greedy_no_ctxModel=Qwen2.5-7B2026.0674.2581.73
Greedy_no_ctxBackbone=Mistral-7B2026.0671.7581.1
Simple InterpBackbone=Llama3-8B, tau=0.252026.067175.83
Simple InterpModel=Llama2-13B, tau=0.252026.0662.7566.74
Simple InterpBackbone=Mistral-7B, tau=0.252026.064560.01
Simple InterpBackbone=Llama3-8B, tau=0.52026.0642.548.7
Simple InterpModel=Qwen2.5-7B, tau=0.252026.0636.553.05
ARRBackbone=Llama3-8B2026.0633.2538.59
Simple InterpModel=Llama2-13B, tau=0.52026.0629.2533.25
Simple InterpBackbone=Mistral-7B, tau=0.52026.0628.543.44
ARRModel=Mistral-7B-Inst2026.0626.537.74
ARRModel=Llama3-8B-Inst2026.0624.535.68
ARRBackbone=Mistral-7B2026.0622.530.66
Simple InterpBackbone=Llama3-8B, tau=0.752026.0617.7524.2
ARRModel=Llama2-13B2026.061723.17
ARRModel=Qwen2.5-7B2026.0615.7522.92
Simple InterpBackbone=Mistral-7B, tau=0.752026.0615.7527.14
Simple InterpModel=Qwen2.5-7B, tau=0.52026.0612.529.81
Simple InterpModel=Llama2-13B, tau=0.752026.0611.2517.9
ARRModel=Llama2-13B-Inst2026.061123.6
GreedyBackbone=Mistral-7B2026.065.2512.99
GreedyBackbone=Llama3-8B2026.064.59.78
Simple InterpModel=Qwen2.5-7B, tau=0.752026.063.515.98
AdaCADBackbone=Llama3-8B2026.063.259.67
GreedyModel=Mistral-7B-Inst2026.062.513.93
AdaCADBackbone=Mistral-7B2026.062.2510.06
GreedyModel=Llama2-13B2026.061.759.58
CADModel=Llama2-13B, alpha=0.252026.061.759.63
AdaCADModel=Llama2-13B2026.061.759.65
COIECDBackbone=Llama3-8B2026.061.756.29
CADBackbone=Mistral-7B, alpha=0.252026.061.759.68
CADModel=Llama2-13B, alpha=0.52026.061.59.13
CoCoAModel=Llama2-13B2026.061.59.13
AdaCADModel=Mistral-7B-Inst2026.061.512.79
CADBackbone=Llama3-8B, alpha=0.252026.061.57.68
GreedyModel=Qwen2.5-7B2026.06110.04
CADModel=Llama2-13B, alpha=0.752026.0618.45
COIECDModel=Llama2-13B2026.0618.62
COIECDModel=Mistral-7B-Inst2026.06111.83
CADBackbone=Llama3-8B, alpha=0.52026.0617.67
CoCoABackbone=Llama3-8B2026.0617.68
COIECDBackbone=Mistral-7B2026.0618.61
AdaCADModel=Qwen2.5-7B2026.060.758.94
GreedyModel=Llama3-8B-Inst2026.060.7511.1
CADBackbone=Llama3-8B, alpha=0.752026.060.757.19
CADBackbone=Llama3-8B, alpha=1.02026.060.757.11
CADBackbone=Mistral-7B, alpha=0.52026.060.758.34
CADModel=Qwen2.5-7B, alpha=0.252026.060.58.46
COIECDModel=Qwen2.5-7B2026.060.57.19
CADModel=Llama2-13B, alpha=1.02026.060.57.75
GreedyModel=Llama2-13B-Inst2026.060.58.9
CADBackbone=Mistral-7B, alpha=0.752026.060.56.75
CoCoABackbone=Mistral-7B2026.060.56.98
CADModel=Qwen2.5-7B, alpha=0.52026.060.257.24
CADModel=Qwen2.5-7B, alpha=0.752026.060.256.75
CADModel=Qwen2.5-7B, alpha=1.02026.060.256.3
CoCoAModel=Qwen2.5-7B2026.060.256.19
CADModel=Llama3-8B-Inst2026.060.259.55
COIECDModel=Llama3-8B-Inst2026.060.2511.33
AdaCADModel=Llama3-8B-Inst2026.060.2510.88
CoCoAModel=Llama3-8B-Inst2026.060.2510.81
CADModel=Mistral-7B-Inst2026.060.2510.61
ARRModel=Qwen2.5-7B-Inst2026.060.2510.75
CADBackbone=Mistral-7B, alpha=1.02026.060.255.47
COIECDModel=Llama2-13B-Inst2026.060.28.7
AdaCADModel=Llama2-13B-Inst2026.060.28.4
CoCoAModel=Mistral-7B-Inst2026.0605.66
GreedyModel=Qwen2.5-7B-Inst2026.0607.74
CADModel=Qwen2.5-7B-Inst2026.0605.32
COIECDModel=Qwen2.5-7B-Inst2026.0606.99
AdaCADModel=Qwen2.5-7B-Inst2026.0607.31
CoCoAModel=Qwen2.5-7B-Inst2026.0606.42
CADModel=Llama2-13B-Inst2026.0607.4
CoCoAModel=Llama2-13B-Inst2026.0605.5