Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Short-form Question Answering on Trivia QA
Loading...
85.9
AUROC
Rewarding Doubt*
48.564
58.257
67.95
77.643
May 29, 2025
AUROC
ECE
Updated 19d ago
Evaluation Results
Method
Method
Links
AUROC
ECE
Rewarding Doubt*
Category=Literature SOTA
2025.05
85.9
2.2
Self-Cons
Category=Baselines
2025.05
73.4
12.2
LOVEC-DPO
Category=Our Methods
2025.05
71.2
6.9
LOVEC-GRPO
Category=Our Methods
2025.05
69.2
6.3
p(true)
Category=Baselines
2025.05
60.1
21.1
LOVEC-SFT
Category=Our Methods
2025.05
56.3
2
Self-Verb
Category=Baselines
2025.05
50
69.3
Feedback
Search any
task
Search any
task