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

Factual Consistency Evaluation on SummEval (test)

66.3Pearson CC

ALIGNSCORE-large

-5.66813.01631.750.384May 26, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.05
66.3
2023.05
61.6
2023.05
61.1
2023.05
57.8
2023.05
54.7
2023.05
50.3
2023.05
50.1
2023.05
42.3
2023.05
41.5
2023.05
41.5
2023.05
41.1
2023.05
40.9
2023.05
35.5
2023.05
34.8
2023.05
33.1
2023.05
29.7
2023.05
28.5
2023.05
24.9
2023.05
23.8
2023.05
21.3
2023.05
-1.8
2023.05
-2.9