Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Detection on FactualBio paragraph-length biographies
Loading...
72.9
AUROC
HalluSE
56.988
61.119
65.25
69.381
Jun 2, 2026
AUROC
AURAC
Acc @ 0.8
Acc @ 0.9
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
AURAC
Acc @ 0.8
Acc @ 0.9
HalluSE
Backbone=Qwen3-32B, SH...
2026.06
72.9
77.3
75.4
72.8
P(True)
Backbone=Qwen3-32B
2026.06
69.8
73.3
70
70
Naive SE
Backbone=Qwen3-32B
2026.06
66.2
73.1
70.5
70.5
Self-Check
Backbone=Qwen3-32B
2026.06
57.6
69.3
73.5
73.5
Feedback
Search any
task
Search any
task