Our new X account is live! Follow @wizwand_team for updates

Refusal Detection on XSTEST-RESP (full)

98.1RR (F1)

GPT-4

Updated 4d ago

Evaluation Results

Method	Links
GPT-4 2024.06		98.1
WILDGUARD 2024.06		92.8
LibrAI-LongFormer-ref 2024.06		74.3
Keyword-based detector 2024.06		71
Llama-Guard2 2024.06		64.1
Llama-Guard 2024.06		62.9
OAI Mod. API 2024.06		58.6
Aegis-Guard-P 2024.06		48.5
Aegis-Guard-D 2024.06		44.2