Share your thoughts, 1 month free Claude Pro on usSee more

Reward-wise QA Fairness and Alignment on GLOBALQA

0.9996FI JS Score

APPA

Updated 1mo ago

Evaluation Results

Method	Links
APPA 2026.04		0.9996	0.9996	0.9993	0.824	0.884	0.882	0.809	0.871	0.857	0.896
PPO/JS 2026.04		0.9995	0.9997	0.9996	0.834	0.886	0.909	0.808	0.862	0.885	0.972
APPA 2026.04		0.9995	0.9996	0.9995	0.848	0.899	0.908	0.834	0.888	0.885	0.977
APPA 2026.04		0.9994	0.9997	0.9995	0.861	0.912	0.916	0.843	0.898	0.891	0.963
PPO/JS 2026.04		0.9994	0.9996	0.9996	0.826	0.876	0.908	0.801	0.854	0.886	0.962
PPO/JS 2026.04		0.9993	0.9996	0.9992	0.81	0.862	0.877	0.786	0.84	0.854	0.905
PPO/JS 2026.04		0.9695	0.9697	0.9696	0.839	0.89	0.914	0.812	0.868	0.89	0.957
PPO/JS 2026.04		0.9694	0.9696	0.9695	0.826	0.879	0.905	0.802	0.857	0.883	0.962
PPO/JS 2026.04		0.9693	0.9694	0.9671	0.726	0.785	0.759	0.706	0.762	0.727	0.889
SFT 2026.04		0.9399	0.9394	0.9389	0.786	0.847	0.855	0.779	0.841	0.84	0.958
SFT 2026.04		0.9394	0.9392	0.9369	0.73	0.791	0.763	0.724	0.788	0.75	0.933
BASE 2026.04		0.9392	0.9392	0.9369	0.73	0.791	0.762	0.723	0.788	0.75	0.94
SFT 2026.04		0.9391	0.9393	0.9381	0.785	0.845	0.862	0.781	0.844	0.857	0.981
BASE 2026.04		0.9389	0.9392	0.9368	0.682	0.783	0.754	0.672	0.773	0.739	0.968
BASE 2026.04		0.9389	0.939	0.9345	0.664	0.745	0.71	0.659	0.741	0.696	0.958