List your company

LLM Jailbreaking on Mistral-7B-Instruct v0.2

77Success Rate First (SRF)Adaptive Probe-based Steering
-2.0418.483959.52May 19, 2026

Evaluation results

MethodLinks
Adaptive Probe-based Steering2026.05779597
RD-A2026.05697992
Angular2026.05688193
RD-C2026.05547787
RepE2026.05223
SCAV2026.05120