List your company

Knowledge Conflict Resolution on Conflicts

65.4Exact Match (EM)SDA
11.8425.74539.6553.555Jun 23, 2026

Evaluation results

MethodLinks
SDAModel=Qwen2.5-7B2026.0665.4—
MADARAModel=Qwen2.5-7B, RSC=Stochastic, ρ̂1=0.46, Strategy=SDA2026.0665.45.5
3-AgentModel=Qwen2.5-7B2026.0665—
3-AgentModel=Gemma-2-9B2026.0664.6—
CoTModel=Gemma-2-9B2026.0663.3—
SDAModel=Gemma-2-9B2026.0663.3—
MADARAModel=Gemma-2-9B, RSC=Stochastic, ρ̂1=0.79, Strategy=SDA2026.0663.32.5
SDAModel=Qwen3-8B2026.0663—
MADARAModel=Qwen3-8B, RSC=Stochastic, ρ̂1=0.39, Strategy=SDA2026.06632.2
3-AgentModel=Qwen3-8B2026.0662.4—
CoTModel=Qwen3-8B2026.0662.4—
CoTModel=Qwen2.5-7B2026.0662.4—
NFModel=Qwen3-8B2026.0660.8—
NFModel=Gemma-2-9B2026.0660.8—
NFModel=Qwen2.5-7B2026.0659.9—
MADARA (Average)2026.0657.114.4
MADARAModel=Llama-3.1-8B, RSC=Quality-Ordered, ρ̂1=0.76, Strategy=PDE2026.0650.236.3
AverageMethod_Group=3-Agent2026.0646.9—
AverageMethod_Group=SDA2026.0646.3—
AverageMethod_Group=CoT2026.0645.5—
MADARAModel=Mistral-7B-v0.3, RSC=Quality-Ordered, ρ̂1=0.35, Strategy=PDE2026.0643.525.4
AverageMethod_Group=NF2026.0642.7—
3-AgentModel=Llama-3.1-8B2026.0624.1—
CoTModel=Mistral-7B-v0.32026.0622.8—
SDAModel=Mistral-7B-v0.32026.0620.3—
SDAModel=Llama-3.1-8B2026.0619.4—
3-AgentModel=Mistral-7B-v0.32026.0618.6—
NFModel=Mistral-7B-v0.32026.0618.1—
CoTModel=Llama-3.1-8B2026.0616.5—
NFModel=Llama-3.1-8B2026.0613.9—