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

Factuality Evaluation on QAGS XSUM

53.9Pearson Correlation

ALIGN

-13.184.23521.6539.065Jun 22, 2021Oct 24, 2021Feb 25, 2022Jun 29, 2022Oct 31, 2022Mar 4, 2023Jul 6, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.07
53.9
2023.07
51.1
2023.07
45.5
2023.07
44.2
2023.07
30.6
2023.07
16.3
2023.07
13.2
2021.06
0.184
2021.06
0.175
2021.06
0.097
2021.06
0.074
2021.06
0.054
2021.06
0.025
2021.06
0.024
2021.06
0.024
2021.06
0.009
2021.06
-0.008
2021.06
-0.094
2023.07
-10.6