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

Abg-CoQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Conversational Question AnsweringAbg-CoQA Unambiguous
Overlap F184.4
10
Conversational Question AnsweringAbg-CoQA Ambiguous
Overlap F172.9
10
Action Level PredictionAbg-CoQA (OOD)
Ambiguous Acc93.44
4
Showing 3 of 3 rows