Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Utility Evaluation on XSTest Safe Prompts
Loading...
97.2
Compliance
FedDPO
92.624
93.812
95
96.188
Apr 8, 2026
Compliance
Refusal Rate
Updated 9d ago
Evaluation Results
Method
Method
Links
Compliance
Refusal Rate
FedDPO
Setting=Poisoned
2026.04
97.2
2.8
FedDetox
Setting=Ours
2026.04
94.4
5.6
Qwen2.5-1.5B-Instruct
Setting=Original
2026.04
92.8
7.2
Feedback
Search any
task
Search any
task
