List your company

Question Answering on PubMedQA 80/20 split (seed 42)

0Pathwise ViolationsCSA
-0.42.357.7May 18, 2026

Evaluation results

MethodLinks
CSAN (EVAL size)=800, Err (Base verifier-fail rate)=23.9%, alpha* (Target risk level)=0.202026.05063.515.1
NEX-ConfN (EVAL size)=800, Err (Base verifier-fail rate)=23.9%, alpha* (Target risk level)=0.202026.051——
5 online baselinesN (EVAL size)=800, Err (Base verifier-fail rate)=23.9%, alpha* (Target risk level)=0.202026.0510——
ConfFactN (EVAL size)=800, Err (Base verifier-fail rate)=23.9%, alpha* (Target risk level)=0.202026.05——7.6