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

Confidence Calibration on Average of four domains Relational Inference Planning

0.114Brier Score

first-second-distance-based (FSD)

Updated 4d ago

Evaluation Results

Method	Links
first-second-distance-based (FSD) 2024.02		0.114
entropy-based consistency 2024.02		0.116
agreement-based consistency 2024.02		0.119
agreement-based consistency 2024.02		0.151
verb_ling 2024.02		0.154
first-second-distance-based (FSD) 2024.02		0.159
entropy-based consistency 2024.02		0.175
p_true (8-shot) 2024.02		0.179
verb_percent 2024.02		0.181
p_true (0-shot) 2024.02		0.188
entropy-based consistency 2024.02		0.205
first-second-distance-based (FSD) 2024.02		0.207
logit 2024.02		0.209
agreement-based consistency 2024.02		0.221
verb_ling 2024.02		0.249
verb_percent 2024.02		0.249
verb_ling 2024.02		0.271
verb_percent 2024.02		0.273