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

Commonsense Reasoning on CommonSenseQA (ACC, BS, ECE, CL)

0.1054BS

Base Model (Q0)

Updated 1mo ago

Evaluation Results

Method
Base Model (Q0) 2026.01	0.1054	82.56	0.0173	-0.7201
Isotonic Regression 2026.01	0.1119	-	0.0219	-0.717
Isotonic Regression 2026.01	0.1135	-	0.019	-0.7145
Base Model (Q0) 2026.01	0.1166	82.88	0.0601	-0.7122
TS (Supervised) 2026.01	0.1166	-	0.0524	-0.7122
Base Model (Q0) 2026.01	0.1166	82.88	0.0601	-0.7122
Temperature Scaling 2026.01	0.1166	-	0.0524	-0.7122
Temperature Scaling 2026.01	0.1193	-	0.064	-0.7087
Histogram Binning 2026.01	0.1249	-	0.0254	-0.7039
Base Model (Q0) 2026.01	0.1252	78.46	0.0524	-0.6594
Isotonic Regression 2026.01	0.1259	-	0.0286	-0.6767
Ours (Label-Free Framework) 2026.01	0.1262	83.37	0.0232	-0.7075
Ours (Label-Free) 2026.01	0.1291	83.29	0.0389	-0.7038
label-free post-processing framework 2026.01	0.1291	83.29	0.0389	-0.7038
Histogram Binning 2026.01	0.1295	-	0.022	-0.6985
Temperature Scaling 2026.01	0.1322	-	0.046	-0.6704
Instruct Model (Q1) 2026.01	0.143	82.88	0.1385	-0.6859
Instruct Model (Q1) 2026.01	0.143	82.88	0.1385	-0.6859
Ours (Label-Free Framework) 2026.01	0.1438	80.67	0.0297	-0.6629
Histogram Binning 2026.01	0.1449	-	0.0283	-0.6577
Instruct Model (Q1) 2026.01	0.1512	82.8	0.1483	-0.6768
Isotonic Regression 2026.01	0.1616	-	0.0427	-0.6247
Base Model (Q0) 2026.01	0.1636	70.84	0.0517	-0.5449
Histogram Binning 2026.01	0.1655	-	0.0445	-0.6207
Ours (Label-Free) 2026.01	0.1657	78.71	0.029	-0.6214
label-free post-processing framework 2026.01	0.1657	78.71	0.029	-0.6214
Isotonic Regression 2026.01	0.169	-	0.0443	-0.5468
Base Model (Q0) 2026.01	0.1698	70.93	0.0342	-0.5395
Base Model (Q0) 2026.01	0.1698	70.93	0.0342	-0.5395
Instruct Model (Q1) 2026.01	0.1703	80.26	0.166	-0.6323
Temperature Scaling 2026.01	0.1727	-	0.0645	-0.5431
TS (Supervised) 2026.01	0.1749	-	0.0935	-0.6114
Temperature Scaling 2026.01	0.1749	-	0.0935	-0.6114
Histogram Binning 2026.01	0.1771	-	0.0354	-0.5633
Isotonic Regression 2026.01	0.1773	-	0.0345	-0.5631
Ours (Label-Free) 2026.01	0.1777	74.3	0.0295	-0.5653
label-free post-processing framework 2026.01	0.1777	74.3	0.0295	-0.5653
TS (Supervised) 2026.01	0.1899	-	0.074	-0.5505
Temperature Scaling 2026.01	0.1899	-	0.074	-0.5505
Histogram Binning 2026.01	0.1934	-	0.0257	-0.5224
Base Model (Q0) 2026.01	0.196	70.27	0.1388	-0.5067
Base Model (Q0) 2026.01	0.196	70.27	0.1388	-0.5067
Base Model (Q0) 2026.01	0.1966	58.56	0.0211	-0.389
Ours (Label-Free Framework) 2026.01	0.2002	71.66	0.0885	-0.5165
Instruct Model (Q1) 2026.01	0.203	78.62	0.1999	-0.5832
Instruct Model (Q1) 2026.01	0.203	78.62	0.1999	-0.5832
Instruct Model (Q1) 2026.01	0.2041	74.04	0.1682	-0.5363
Instruct Model (Q1) 2026.01	0.2041	74.04	0.1682	-0.5363
Isotonic Regression 2026.01	0.2309	-	0.0155	-0.3359
Temperature Scaling 2026.01	0.235	-	0.0315	-0.3318
Histogram Binning 2026.01	0.237	-	0.0236	-0.3297
Instruct Model (Q1) 2026.01	0.2579	71.58	0.2574	-0.4579
Ours (Label-Free Framework) 2026.01	0.2847	56.67	0.2182	-0.2821
Instruct Model (Q1) 2026.01	0.3775	56.67	0.3767	-0.1893