List your company

Hallucination Detection on CDM (test)

75F1 ScorePoolingE
41.7250.365967.64Dec 28, 2023

Evaluation results

MethodLinks
PoolingEClassifier architecture=Ensembled, Training data distribution=Organic2023.1275
PoolingSLClassifier architecture=Single-layer, Training data distribution=Organic2023.1273
SummaCzsModel variant=Zero-shot2023.1268
SummaCConvModel variant=Convolutional2023.1267
PoolingE-SYNTHClassifier architecture=Ensembled, Training data distribution=Synthetic2023.1266
PoolingSL-SYNTHClassifier architecture=Single-layer, Training data distribution=Synthetic2023.1265
Seq-Logprob2023.1264
ChatGPTPrompting strategy=Standard2023.1263
QuestEval2023.1261
FActScore2023.1261
Expert Human2023.1255
DAE2023.1253
ChatGPT CoTPrompting strategy=Chain-of-thought2023.1253
FactCC2023.1251
FEQA2023.1244
Optimized Coin (OC)Threshold optimization=Validation set tuned2023.1243