Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination monitoring on Modern History domain
Loading...
84
AUROC
HalMit
46.56
56.28
66
75.72
Jul 21, 2025
AUROC
AUC-PR
F1 Score
Accuracy
Updated 19d ago
Evaluation Results
Method
Method
Links
AUROC
AUC-PR
F1 Score
Accuracy
HalMit
Backbone=Llama2
2025.07
84
80
77
89
HalMit
Backbone=Llama3.1
2025.07
84
84
67
89
SCG
Backbone=Llama2
2025.07
78
79
81
82
SCG
Backbone=Llama3.1
2025.07
78
77
60
76
PP
Backbone=Llama2
2025.07
74
76
73
79
ICL
Backbone=Llama2
2025.07
69
67
64
67
ICL
Backbone=Llama3.1
2025.07
59
55
54
61
PP
Backbone=Llama3.1
2025.07
48
45
46
56
Feedback
Search any
task
Search any
task