Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-inject detection (benign task-switch) on BIPIA code-QA
Loading...
13
FPR
LCF (Qwen-2.5-7B)
12.76
14.38
16
17.62
Apr 27, 2026
FPR
TPR
TPR - FPR
Cohen's d
Metric > 0 Threshold
Updated 1mo ago
Evaluation Results
Method
Method
Links
FPR
TPR
TPR - FPR
Cohen's d
Metric > 0 Threshold
LCF (Qwen-2.5-7B)
Backbone=Qwen-2.5-7B,...
2026.04
13
100
87
1.87
100
LCF (Gemma-2-9B)
Backbone=Gemma-2-9B, E...
2026.04
14
100
86
3.11
100
LCF (Llama-3-8B)
Backbone=Llama-3-8B, E...
2026.04
17
100
83
1.36
100
LCF (Qwen-2.5-14B)
Backbone=Qwen-2.5-14B,...
2026.04
19
100
81
1.47
99
Feedback
Search any
task
Search any
task