List your company

Hallucination Detection on DiverseSumm+

79.5Macro F1VeriTrail
17.6233.68549.7565.815May 27, 2025

Evaluation results

MethodLinks
VeriTrailq=3, Base Model=gpt-4o-2024-08-062025.0579.576.387.196.784.555.9
VeriTrailq=1, Base Model=gpt-4o-2024-08-062025.0576.68395.876.255.189.8
RAGk=15, Base Model=gpt-4o-2024-08-062025.0575.17486.790.566.457.5
Bespoke-MiniCheck-7Bk=2, tau=0.5, full_name=Llama-3.1-Bespoke-MiniCheck-7B2025.0572.169.483.895.475.343.3
VeriTrailModel=Gemini 2.5 Flash, q=12025.0569.972.387.277.350.867.3
RAGModel=Gemini 2.5 Flash, k=102025.0568.967.582.590.161.144.9
VeriTrailModel=DeepSeek, q=12025.056873.289.868.846.377.6
RAGModel=Mistral, k=102025.0567.666.582.288.256.844.7
VeriTrailModel=Mistral, q=12025.056773.891.764.744.883
RAGModel=DeepSeek, k=302025.056663.980.197.278.930.6
GPT-4.1 Mini2025.0562.961.580.393.860.729.1
AlignScorek=1, tau=0.92025.0560.462.782.870.337.655.1
Gemini 1.5 Pro2025.0549.857.682.245.129.470.1
INFUSEtau=0.52025.052050.11000.324.6100