List your company

Jailbreak Defense on 100 dialogue samples (test)

2ASR (Low Difficulty)Self-Reminder
0.2811.8923.535.11Jan 7, 2026

Evaluation results

MethodLinks
Self-ReminderModel=GPT-3.5-turbo-1106, Max Tokens=1200, Temperature=0.8, Top-p=1, Presence Penalty=12026.01213514
HoneyTrapModel=GPT-3.5-turbo-1106, Max Tokens=1200, Temperature=0.8, Top-p=1, Presence Penalty=12026.01742654
GoalPriorityModel=GPT-3.5-turbo-1106, Max Tokens=1200, Temperature=0.8, Top-p=1, Presence Penalty=12026.0113869
PATModel=GPT-3.5-turbo-1106, Max Tokens=1200, Temperature=0.8, Top-p=1, Presence Penalty=12026.0133192221
RPOModel=GPT-3.5-turbo-1106, Max Tokens=1200, Temperature=0.8, Top-p=1, Presence Penalty=12026.0145223923