Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Uncertainty Estimation on HotpotQA (test)
Loading...
72.79
AUPRC
Signatures
52.9988
58.1369
63.275
68.4131
Mar 17, 2026
AUPRC
Updated 24d ago
Evaluation Results
Method
Method
Links
AUPRC
Signatures
Train Dataset=HotpotQA...
2026.03
72.79
Signatures
Train=HotpotQA, Backbo...
2026.03
72.79
ACT-ViT
Train Dataset=TriviaQA...
2026.03
67.57
ACT-ViT
Train Dataset=IMDB, Mo...
2026.03
67.16
Signatures
Train Dataset=TriviaQA...
2026.03
63.83
Signatures
Train Dataset=IMDB, Mo...
2026.03
59.21
Signatures
Train=IMDB, Backbone=M...
2026.03
59.21
LOS-NET
Train=HotpotQA, Backbo...
2026.03
58.96
LOS-NET
Train=Movies, Backbone...
2026.03
58.96
LOS-NET
Train=IMDB, Backbone=M...
2026.03
58.96
ACT-ViT
Train Dataset=HotpotQA...
2026.03
54.34
Signatures
Train=Movies, Backbone...
2026.03
53.76
Feedback
Search any
task
Search any
task