Safety

PKU-SafeRLHF

PKU-SafeRLHF per-response safety ratings for Alpaca-family models.

39,994items
3subjects
CC-BY-NC-4.0license
safetydomain
textmodality
item-level responses released
Saturation status: Unknown

Response matrix

Fit to width. Hover for subject & item; click a cell for details.

PKU-SafeRLHF response matrix: AI models (rows) against items (columns)
Correct (1)Incorrect (0)Unobserved

Scale: 1 = correct · 0 = incorrect

Subjects

  1. 1Alpaca3-8B0.4997
  2. 2Alpaca2-7B0.4892
  3. 3Alpaca-7B0.4676