Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Clarification on AmbigQA High Aleatoric Uncertainty Superset (top 20% examples)
Loading...
43.87
Clarification Rate
ICE
33.2412
36.0006
38.76
41.5194
May 27, 2026
Clarification Rate
Delta H (ΔH)
Edit Distance
Updated 1mo ago
Evaluation Results
Method
Method
Links
Clarification Rate
Delta H (ΔH)
Edit Distance
ICE
Backbone=GPT-4
2026.05
43.87
-0.0633
6.7878
Deep Ensembles
Backbone=GPT-4
2026.05
38.31
-0.0076
7.4545
Semantic Entropy
Backbone=GPT-4
2026.05
34.23
0.033
6.4545
ShaQ
Backbone=GPT-4
2026.05
33.65
0.0389
5.5151
Feedback
Search any
task
Search any
task