DialogSum
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
DialogSum
99.1Reasoning
33
DIALOGSUM
51.6ROUGE-L
27
DialogSum
48.36R-L
24
DialogSum
36.45ROUGE-L
14
DialogSum
0.187ROUGE-L
11
DialogSum 1.5k examples (val)
39.1ROUGE-L
11
DIALOGSUM
0.83Std Dev ROUGE-1
8
DialogSum
20.45Extent
7
DialogSum Single Client
50.92ROUGE-1
6
DialogSum (DS)
0Toxic Fraction
5
DialogSum (DS)
0.1Sentiment Parity
5
DialogSum (DS)
5.6Stereotype Fraction
5
DialogSum 50 samples (test)
4.03Informativeness
3