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

DIALFACT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Claim VerificationDIALFACT (val)
Accuracy70.4
18
Claim VerificationDIALFACT (test)
Accuracy69.2
18
Document RetrievalDIALFACT (test)
Recall0.75
5
Verifiable Claim DetectionDIALFACT (test)
Accuracy82.8
4
Evidence Sentence SelectionDIALFACT (test)
Recall@575.4
4
Showing 5 of 5 rows