List your company

Question Answering on TAT-QA (eval)

8.2RiskCSA
7.797.9958.28.405May 18, 2026

Evaluation results

MethodLinks
CSAN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.058.249.90
CRCN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.058.2——
LTTN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.058.2——
ConfFactN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.058.2——
5 online baselinesN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.05——10
NEX-ConfN (EVAL size)=565, Err (Base verifier-fail rate)=25.7%, alpha* (Target risk level)=0.202026.05——0