Harmful-request assistance on SORRY-Bench linguistic mutations
25.4Compliance RateQwen3.5-27B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-27BSystem Prompt=default (none), Judge=ft-mistral-7b-instruct-v0.22026.06 | 25.4 | |
| Qwen3.5-27BSystem Prompt=v0 (generic helpful-assistant), Judge=ft-mistral-7b-instruct-v0.22026.06 | 25.4 | |
| Qwen3.5-27BSystem Prompt=v1 (PSYCHOSAFE prompt), Judge=ft-mistral-7b-instruct-v0.22026.06 | 19 | |
| Qwen3.5-27B-psysafeSystem Prompt=v1 (PSYCHOSAFE prompt), Judge=ft-mistral-7b-instruct-v0.22026.06 | 0.1 | |
| Qwen3.5-27B-psysafeSystem Prompt=default (none), Judge=ft-mistral-7b-instruct-v0.22026.06 | 0 | |
| Qwen3.5-27B-psysafeSystem Prompt=v0 (generic helpful-assistant), Judge=ft-mistral-7b-instruct-v0.22026.06 | 0 |