Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object Hallucination Detection on POPE random
Loading...
89.1
F1 Score
RSP
-2.63944
21.17753
44.9945
68.81147
May 27, 2026
F1 Score
Trigger Percentage
Updated 6d ago
Evaluation Results
Method
Method
Links
F1 Score
Trigger Percentage
RSP
Model=InstructBLIP, Pr...
2026.05
89.1
10
Baseline
Model=InstructBLIP
2026.05
88.7
-
Always-on
Model=InstructBLIP, Pr...
2026.05
87.4
-
RSP
Model=LLaVA-1.5, Routi...
2026.05
0.899
7
Baseline
Model=LLaVA-1.5
2026.05
0.896
-
Always-on
Model=LLaVA-1.5
2026.05
0.889
-
Feedback
Search any
task
Search any
task