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

P4G

Benchmarks

Task NameDataset NameSOTA ResultTrend
Charity PersuasionP4G User Simulation
Success Rate (SR)78
16
Dialogue Response GenerationP4G (test)
Accuracy89
3
Interactive Persuasive DialogueP4G (interactive)
Competence4.21
2
Showing 3 of 3 rows