Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Selective Answering on ALCUNA Unanswerable
Loading...
96.2
Abstain Rate
SaySelf
20.488
40.144
59.8
79.456
Jul 2, 2026
Abstain Rate
Updated 23d ago
Evaluation Results
Method
Method
Links
Abstain Rate
SaySelf
2026.07
96.2
C3RL
Configuration=Ours
2026.07
73.4
RLCR
2026.07
66.5
C3RL
Ablation=w/o Ref
2026.07
59.5
Base
2026.07
24.7
RLVR
2026.07
23.4
Feedback
Search any
task
Search any
task
