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

Uncertainty Estimation on TriviaQA (test)

87.91AUROC

ACT-ViT

55.09863.616572.13580.6535Jul 3, 2023Dec 26, 2023Jun 20, 2024Dec 14, 2024Jun 8, 2025Dec 2, 2025May 28, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.03
87.91---
2026.05
86.12--93.02
2026.04
85.7---
2026.04
84.9---
2026.04
84.8---
2026.04
84.4---
2026.04
83.4---
2026.04
83.4---
2026.04
83.3---
2026.04
83.3---
2026.04
83.3---
2026.04
83.3---
2026.04
83.2---
2026.04
83.2---
2026.04
83.2---
2026.04
83.2---
2026.04
83.2---
2026.04
83.2---
2026.03
82.66---
2025.05
82.1212.761.2-
2025.05
81.913.760.98-
2026.05
81.89--93.09
2023.07
81.8---
2023.07
81.4---
2025.05
8127.050.34-
2025.05
80.9213.07--
2025.05
80.9216.17--
2025.05
80.6636.64--
2025.05
80.2137.851.97-
2026.05
80.19--92.82
2026.05
80.19--92.82
2023.07
80---
2025.05
79.9320.81.57-
2025.05
79.9313.70.38-
2025.05
79.5516.4--
2023.07
79.3---
2025.05
78.6731.023.35-
2025.05
78.3732.29--
2023.07
78.3---
2025.05
78.2440.14--
2025.05
77.09202.95-
2023.07
75.8---
2026.04
75.5---
2026.04
75.5---
2026.04
75.5---
2026.04
75.4---
2025.05
75.3240.61--
2023.07
74.9---
2023.07
74.9---
2025.05
74.8916.7812.55-
2025.05
74.7911.532.24-
2023.07
74.5---
2023.07
74.4---
2023.07
74.3---
2025.05
72.5514.31--
2025.05
72.2932.635.84-
2025.05
72.2919.8415.15-
2023.07
71.6---
2023.07
71.5---
2023.07
71.3---
2026.05
71.23--89.73
2026.03
71.19---
2023.07
71---
2025.05
70.5527.6110.15-
2023.07
70.4---
2025.05
69.8723.17--
2026.05
69.83--86.96
2025.05
69.827.4150.25-
2023.07
69.8---
2025.05
69.7617.245.25-
2023.07
69.2---
2023.07
69---
2025.05
66.7445--
2025.05
66.6220.2810.25-
2023.07
65.7---
2023.07
65.5---
2023.07
65.4---
2023.07
65.2---
2025.05
65.1141.7618.62-
2023.07
65.1---
2023.07
64.7---
2023.07
64.7---
2025.05
64.5221.38--
2023.07
64.4---
2023.07
63.9---
2023.07
63.5---
2023.07
63.4---
2023.07
63---
2023.07
62.7---
2023.07
62.4---
2025.05
62.3423.41--
2023.07
62.2---
2026.03
62.01---
2023.07
61.5---
2023.07
61.5---
2025.05
60.4149.13--
2026.03
58.42---
2025.05
57.1424.67--
2023.07
56.5---
2025.05
56.3642.39--
Showing 100 of 110 rows