List your company

Calibration on HotPotQA Hard

0.13Top-1 ECERLCR Single
0.1160.21050.3050.3995Mar 25, 2026

Evaluation results

MethodLinks
RLCR SingleRL Algorithm=RLCR, Output Mode=Single, k=32026.030.13——0.16—
RLCR SingleAnswer Setting=Single, k=32026.030.13——0.16—
RLCR MultiRL Algorithm=RLCR, Output Mode=Multi, k=32026.030.310.440.210.220.12
RLCR MultiAnswer Setting=Multi, k=32026.030.310.440.210.220.12
RLVR MultiRL Algorithm=RLVR, Output Mode=Multi, k=32026.030.380.470.220.30.16
RLVR MultiAnswer Setting=Multi, k=32026.030.380.470.220.30.16
RLVR SingleRL Algorithm=RLVR, Output Mode=Single, k=32026.030.48——0.38—
RLVR SingleAnswer Setting=Single, k=32026.030.48——0.38—