Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Faithfulness detection on AggreFact 2023
Loading...
69.9
Balanced Accuracy (CNN)
MiniCheck-Flan-T5-L
49.204
54.577
59.95
65.323
Jun 11, 2026
Balanced Accuracy (CNN)
Balanced Accuracy (XSum)
Average Balanced Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Balanced Accuracy (CNN)
Balanced Accuracy (XSum)
Average Balanced Accuracy
MiniCheck-Flan-T5-L
Backbone=Flan-T5-L, Su...
2026.06
69.9
74.3
72.1
OT Detector (T5-base)
Backbone=T5-base, Supe...
2026.06
57.2
57.6
57.4
OT Detector (Flan-T5-large)
Backbone=Flan-T5-large...
2026.06
55.6
61.4
58.5
Random baseline
Supervision=None, Thre...
2026.06
50
50
50
Feedback
Search any
task
Search any
task