Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Context Attribution on HotpotQA distractor (val)
Loading...
78
P@1
CAMAB
2.6
22.175
41.75
61.325
Jun 24, 2025
P@1
F1@2
F1@k*
AUROC
AP
Updated 1mo ago
Evaluation Results
Method
Method
Links
P@1
F1@2
F1@k*
AUROC
AP
CAMAB
Base Model=LLaMA-3.1-8...
2025.06
78
60.7
61.6
85.5
68.8
SHAP
Base Model=LLaMA-3.1-8...
2025.06
68
51.1
51.3
80.6
59.8
Random
Base Model=LLaMA-3.1-8...
2025.06
5.5
5.8
7.1
51.6
16.2
Feedback
Search any
task
Search any
task
