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

RolePlayConv

Benchmarks

Task NameDataset NameSOTA ResultTrend
Turn-taking decisionRolePlayConv zero-shot (test)
Precision79
4
Response generationRolePlayConv (evaluation set)
Response Score7.4
3
Turn-takingRolePlayConv (eval)
Turn-Taking Score72
3
Showing 3 of 3 rows