Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

QAGS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Factual Consistency EvaluationQAGS-XSum
Spearman Correlation57.4
39
Factual Consistency EvaluationQAGS CNNDM
Spearman Correlation73.9
38
Factual Consistency EvaluationQAGS-CNNDM (test)
Pearson Correlation Coefficient78.1
22
Factual Consistency EvaluationQAGS-XSum (test)
Pearson Correlation Coefficient5.27
22
Factuality EvaluationQAGS XSUM
Pearson Correlation53.9
19
Factuality EvaluationQAGS CNN
Pearson Correlation0.735
11
Factual Consistency EvaluationQAGS-X
Pearson Correlation (rp)0.618
5
Factual Consistency EvaluationQAGS-C
Pearson Correlation (rp)0.785
5
Showing 8 of 8 rows