List your company

Question Answering on Overall (EM, F1, Trigger rate (T))

41.6EMVerbal-Calibrate
5.09614.57324.0533.527Apr 7, 2026

Evaluation results

MethodLinks
Verbal-CalibrateScope=global2026.0441.650.548.1
Uncertain-CalibrateScope=local2026.0440.948.161.4
DRAGIN2026.0432.743.276.8
Ret-All2026.0428.436.4100
ADARAGUE2026.0427.835.443.8
No-Ret2026.0425.933.1—
Base-Verbal2026.0421.827.913.1
FLARE2026.0420.830.699
Base-UncTok2026.0420.527.23.5
SR-13BBackbone=13B2026.048.822.429.5
SR-7BBackbone=7B2026.046.516.746.2