List your company

Knowledge Conflict Resolution on PAVE (test)

59IEJSD-based arbitration
4.150418.390232.6346.8698May 31, 2026

Evaluation results

MethodLinks
JSD-based arbitrationBackbone=Llama3-8B, K=5, Temperature=1.02026.055965.262.1
ContextEvalBackbone=Qwen3-32B2026.0558.4964.2561.47
ExplicitSCRBackbone=Gemini-2.5-flash2026.0557.566.9362.22
JSD-based arbitrationBackbone=Qwen3-32B, K=5, Temperature=1.02026.0556.869.1262.97
ContextEvalBackbone=Gemini-2.5-flash2026.0555.6138.7347.17
JSD-based arbitrationBackbone=Gpt-4o-mini, K=5, Temperature=1.02026.0555.3867.1461.26
ContextEvalBackbone=Gpt-4o-mini2026.0555.267.0361.12
ContextEvalBackbone=Llama3-8B2026.0554.9261.1758.05
ExplicitSCRBackbone=Gpt-4o-mini2026.0554.1264.3559.24
InternalEvalBackbone=Qwen3-32B2026.0552.6359.2955.96
ContextEvalBackbone=Phi-42026.0552.566.659.55
JSD-based arbitrationBackbone=Phi-4, K=5, Temperature=1.02026.0552.463.658
ContextConfBackbone=Phi-42026.0552.252.252.2
InternalEvalBackbone=Gpt-4o-mini2026.0551.4357.654.52
JSD-based arbitrationBackbone=Mistral-7B, K=5, Temperature=1.02026.0551.262.9657.08
TPCBackbone=Phi-42026.0551.1451.1451.14
JSD-based arbitrationBackbone=Gemini-2.5-flash, K=5, Temperature=1.02026.0551.1265.0158.07
InternalEvalBackbone=Llama3-8B2026.0551.0458.3954.72
ImplicitSCRBackbone=Llama3-8B2026.0550.46055.2
ImplicitSCRBackbone=Phi-42026.0550.160.855.45
InternalEvalBackbone=Gemini-2.5-flash2026.0549.9555.8152.88
ContextConfBackbone=Gpt-4o-mini2026.0547.964.756.3
ImplicitSCRBackbone=Qwen3-32B2026.0547.7760.0853.93
InternalConfBackbone=Gpt-4o-mini2026.0547.648.448
InternalEvalBackbone=Phi-42026.0547.648.848.2
TPCBackbone=Gpt-4o-mini2026.0546.961.654.25
InternalConfBackbone=Phi-42026.0546.665.255.9
ImplicitSCRBackbone=Gpt-4o-mini2026.0545.4859.8852.68
TACS-LRBackbone=Phi-42026.0545.251.847.15
TACS-LRBackbone=Qwen3-32B2026.0545.251.848.5
TACS-LRBackbone=Gpt-4o-mini2026.0544.65449.3
TPCBackbone=Mistral-7B2026.0543.3357.6750.5
ExplicitSCRBackbone=Phi-42026.0541.8150.8446.33
TACS-LRBackbone=Gemini-2.5-flash2026.0539.55346.25
TACS-LRBackbone=Mistral-7B2026.0537.247.842.5
ImplicitSCRBackbone=Mistral-7B2026.0534.5638.8336.7
InternalConfBackbone=Mistral-7B2026.0534.3334.3334.33
ExplicitSCRBackbone=Llama3-8B2026.0532.638.635.6
TACS-LRBackbone=Llama3-8B2026.0528.634.631.6
ContextEvalBackbone=Mistral-7B2026.0527.6110.3318.97
ExplicitSCRBackbone=Qwen3-32B2026.0519.2723.5521.41
ContextConfBackbone=Mistral-7B2026.0515.3310.3312.83
ImplicitSCRBackbone=Gemini-2.5-flash2026.0514.921.8518.38
ExplicitSCRBackbone=Mistral-7B2026.0510.3318.7714.55
InternalEvalBackbone=Mistral-7B2026.056.263.084.67