List your company

Factual Consistency Evaluation on QAGS CNNDM

73.9Spearman CorrelationALIGNSCORE-large
-20.0124.36928.7553.131May 26, 2023Jun 1, 2023Jun 8, 2023Jun 15, 2023Jun 22, 2023Jun 29, 2023Jul 6, 2023

Evaluation results

MethodLinks
ALIGNSCORE-largeBackbone=ROBERTa (355M)2023.0573.9
ALIGNSCORE-largeType=Ours2023.0573.9
ALIGN-largeModel Parameters=355M2023.0771.6
ALIGNModel size=large2023.0771.6
ALIGNSCORE-baseBackbone=ROBERTa (125M)2023.0569
ALIGNSCORE-baseType=Ours2023.0569
G-EVAL-4Backbone=GPT42023.0568.5
G-EVAL-4Model ID=GPT42023.0768.5
BARTScoreType=Misc2023.0568.1
BARTScore2023.0768.1
UniEvalType=Misc2023.0567.6
UniEval2023.0767.6
QAFactEvalType=QA2023.0563.1
QAFactEval2023.0763.1
SummaC-CONVType=NLI2023.0558.4
CTCType=Misc2023.0557.3
CTC2023.0757.3
ALIGN-baseModel Parameters=125M2023.0756.1
ALIGNModel size=base2023.0756.1
BLEUType=Similarity Matching2023.0555.4
ROUGE-2Type=Similarity Matching2023.0555.2
ROUGE-LType=Similarity Matching2023.0553.7
ROUGE-1Type=Similarity Matching2023.0553.6
G-EVAL-3.5Backbone=GPT3.5-d032023.0551.6
G-EVAL-3.5Model ID=GPT3.5-d032023.0751.6
SummaC-ZSType=NLI2023.0551.1
SimCSEType=Similarity Matching2023.0547.2
BERTScoreType=Similarity Matching2023.0546.2
BERTScore2023.0746.2
BLEURTType=Regression2023.0543.4
BLEURT2023.0743.4
FactCCType=Misc2023.0540.3
DAEType=NLI2023.0537.1
QuestEvalType=QA2023.0530.8
BLANCType=Misc2023.0522.2
NER-OverlapType=Similarity Matching2023.050.2
FEQAType=QA2023.05-7.2
MNLIType=NLI2023.05-16.4