List your company

Factual Consistency Evaluation on SummEval

46.6Spearman CorrelationALIGNSCORE-large
-8.7285.6362034.364May 26, 2023Jun 1, 2023Jun 8, 2023Jun 15, 2023Jun 22, 2023Jun 29, 2023Jul 6, 2023

Evaluation results

MethodLinks
ALIGNSCORE-largeType=Ours2023.0546.6
UniEvalType=Misc2023.0544.3
ALIGNSCORE-baseType=Ours2023.0543.4
QAFactEvalType=QA2023.0542.8
CTCType=Misc2023.0541.7
SummaC-CONVType=NLI2023.0541.4
BARTScoreType=Misc2023.0539.1
ROUGE-LType=Similarity Matching2023.0538.5
SummaC-ZSType=NLI2023.0538.3
ROUGE-1Type=Similarity Matching2023.0538.1
ROUGE-2Type=Similarity Matching2023.0537.8
DAEType=NLI2023.0536.2
BLEUType=Similarity Matching2023.0534.7
FactCCType=Misc2023.0533.5
BERTScoreType=Similarity Matching2023.0531.5
SimCSEType=Similarity Matching2023.0526.4
QuestEvalType=QA2023.0526.3
BLEURTType=Regression2023.0523.6
NER-OverlapType=Similarity Matching2023.0521.4
BLANCType=Misc2023.0519
G-EVAL-4Model ID=GPT42023.070.507
ALIGN-largeModel Parameters=355M2023.070.479
ALIGNModel size=large2023.070.479
GPTScoreModel ID=GPT3.5-d032023.070.475
UniEval2023.070.443
ChatGPTModel ID=GPT3.5-turbo2023.070.433
QAFactEval2023.070.428
ALIGN-baseModel Parameters=125M2023.070.42
ALIGNModel size=base2023.070.42
CTC2023.070.417
BARTScore2023.070.391
G-EVAL-3.5Model ID=GPT3.5-d032023.070.386
BERTScore2023.070.315
BLEURT2023.070.236
FEQAType=QA2023.050.2
MNLIType=NLI2023.05-6.6