Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Evaluation of Text Generation on RotoWire-FG (test)
Loading...
3.63
Coherence
BART
2.9436
3.1218
3.3
3.4782
Nov 28, 2025
Coherence
Fluency
Information Coverage (InfoCov)
Incoherence Accuracy (IncoAcc)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Coherence
Fluency
Information Coverage (InfoCov)
Incoherence Accuracy (IncoAcc)
BART
2025.11
3.63
4.27
3.87
3.37
HunterAug-BART
Backbone=BART
2025.11
3.57
3.73
4.13
4.03
HunterAug-T5
Backbone=T5
2025.11
3.4
3.57
4.1
3.97
T5
2025.11
3.2
4.2
3.47
3.17
AuxEncoder
2025.11
2.97
3.67
3.3
2.93
Feedback
Search any
task
Search any
task