Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counterfactual Hallucination Detection on ROCO v2
Loading...
74.9
Pairwise Accuracy
Soft-MSD
71.572
72.436
73.3
74.164
May 7, 2026
Pairwise Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Pairwise Accuracy
Soft-MSD
Backbone=BiomedCLIP [44]
2026.05
74.9
MSD
Backbone=BiomedCLIP [44]
2026.05
73.3
CLIPScore
Backbone=BiomedCLIP [44]
2026.05
71.7
Feedback
Search any
task
Search any
task
