List your company

Hallucination Detection on WMT DE-EN 18 (test)

91.72AUROCLaBSE
78.865682.202885.5488.8772Dec 19, 2022

Evaluation results

MethodLinks
LaBSEdetector_type=External2022.1291.7226.91
Wass-Combodetector_type=Model-based, aggregation=mean scores across five random seeds2022.1287.1747.56
CometKiwidetector_type=External2022.1286.9653.61
Wass-to-Datadetector_type=Model-based, aggregation=mean scores across five random seeds2022.1284.248.15
Seq-Logprobdetector_type=Model-based2022.1283.459.02
Wass-to-Unifdetector_type=Model-based2022.1280.3772.22
Attn-ign-SRCdetector_type=Model-based2022.1279.3672.83