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

Factual Consistency Evaluation on QAGS-XSum (Spearman correlation)

57.4Spearman Correlation

ALIGN-large

-11.5526.34924.2542.151May 26, 2023Jun 1, 2023Jun 8, 2023Jun 15, 2023Jun 22, 2023Jun 29, 2023Jul 6, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.07
57.4
2023.07
57.4
2023.05
57.2
2023.07
53.7
2023.07
52.7
2023.07
52.7
2023.05
51.9
2023.05
50
2023.07
50
2023.05
45
2023.05
44.1
2023.07
44.1
2023.05
43.7
2023.07
40.6
2023.05
37.5
2023.05
31.2
2023.05
30.6
2023.07
30.6
2023.05
28.8
2023.07
22
2023.05
18.1
2023.05
17.7
2023.05
17
2023.07
17
2023.05
16.5
2023.05
12.4
2023.07
12.4
2023.05
11.9
2023.05
11.2
2023.05
10.1
2023.05
1.6
2023.05
0.7
2023.05
0.572
2023.05
0.537
2023.05
0.519
2023.05
0.406
2023.05
-6.5
2023.05
-8.9
2023.07
-8.9