List your company

Factual Consistency Evaluation on QAGS-XSum (Spearman correlation)

57.4Spearman CorrelationALIGN-large
-11.5526.34924.2542.151May 26, 2023Jun 1, 2023Jun 8, 2023Jun 15, 2023Jun 22, 2023Jun 29, 2023Jul 6, 2023

Evaluation results

MethodLinks
ALIGN-largeModel Parameters=355M2023.0757.4
ALIGNModel size=large2023.0757.4
ALIGNSCORE-largeType=Ours2023.0557.2
G-EVAL-4Model ID=GPT42023.0753.7
ALIGN-baseModel Parameters=125M2023.0752.7
ALIGNModel size=base2023.0752.7
ALIGNSCORE-baseType=Ours2023.0551.9
UniEvalType=Misc2023.0550
UniEval2023.0750
SummaC-CONVType=NLI2023.0545
QAFactEvalType=QA2023.0544.1
QAFactEval2023.0744.1
SummaC-ZSType=NLI2023.0543.7
G-EVAL-3.5Model ID=GPT3.5-d032023.0740.6
DAEType=NLI2023.0537.5
NER-OverlapType=Similarity Matching2023.0531.2
CTCType=Misc2023.0530.6
CTC2023.0730.6
FactCCType=Misc2023.0528.8
GPTScoreModel ID=GPT3.5-d032023.0722
ROUGE-1Type=Similarity Matching2023.0518.1
ROUGE-2Type=Similarity Matching2023.0517.7
BARTScoreType=Misc2023.0517
BARTScore2023.0717
ROUGE-LType=Similarity Matching2023.0516.5
BLEURTType=Regression2023.0512.4
BLEURT2023.0712.4
QuestEvalType=QA2023.0511.9
SimCSEType=Similarity Matching2023.0511.2
BLEUType=Similarity Matching2023.0510.1
BLANCType=Misc2023.051.6
MNLIType=NLI2023.050.7
ALIGNSCORE-largeBackbone=ROBERTa (355M)2023.050.572
G-EVAL-4Backbone=GPT42023.050.537
ALIGNSCORE-baseBackbone=ROBERTa (125M)2023.050.519
G-EVAL-3.5Backbone=GPT3.5-d032023.050.406
FEQAType=QA2023.05-6.5
BERTScoreType=Similarity Matching2023.05-8.9
BERTScore2023.07-8.9