← back to paper

Review history

arxiv: 2606.31644 · 2 revisions

Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues

1. 2026-07-03 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   20490 ms 5733 in 1092 out 2026-07-03T21:59:04.604453+00:00
2. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   26909 ms 5740 in 1012 out 2026-07-01T05:24:31.062151+00:00