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

Factuality Evaluation on AggreFact CNN (EXF)

76.5Balanced Accuracy

SummaC-ZS

48.9456.09563.2570.405Mar 4, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.03
76.5
2024.03
73.9
2024.03
69.8
2024.03
69.1
2024.03
68.8
2024.03
67.9
2024.03
67.8
2024.03
65.8
2024.03
64.5
2024.03
64.3
2024.03
63.6
2024.03
60.4
2024.03
57.7
2024.03
52.8
50