Our new X account is live! Follow @wizwand_team for updates

Confidence Calibration on MultiNLI Mismatch (test)

0.0071ECE

MIR

Updated 4d ago

Evaluation Results

Method	Links
MIR 2023.06		0.0071	0.0107	0.0026	0.0258
IR 2023.06		0.0088	0.0107	0.0036	0.0246
MIR + PROCAL 2023.06		0.0103	0.0136	0.004	0.0235
HB + PROCAL 2023.06		0.0105	0.015	0.0025	0.0251
HB 2023.06		0.0111	0.0117	0.0036	0.0376
TS + PROCAL 2023.06		0.0122	0.0135	0.004	0.0278
ETS + PROCAL 2023.06		0.0124	0.0126	0.0039	0.0277
IR + PROCAL 2023.06		0.0143	0.0123	0.0034	0.0261
Conf + PROCAL 2023.06		0.0145	0.0146	0.0037	0.0278
ETS 2023.06		0.0158	0.0156	0.0066	0.0304
TS 2023.06		0.017	0.0176	0.0041	0.0303
PTS + PROCAL 2023.06		0.0242	0.0246	0.0093	0.0356
Conf 2023.06		0.0247	0.0262	0.0085	0.0354
PTSK + PROCAL 2023.06		0.0426	0.044	0.0283	0.0515
PTS 2023.06		0.0753	0.075	0.0421	0.0778
PTSK 2023.06		0.1014	0.1014	0.074	0.1033