Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PVP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Persuasiveness classificationPVP (test)
Balanced Accuracy76.6
12
Rationale Faithfulness EvaluationPVP
R-D Consistency99.5
6
Showing 2 of 2 rows