Pith. sign in

← back to paper

Review history

arxiv: 2605.03217 · 3 revisions

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

  1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 5.0
    36374 ms 5872 in 1209 out 2026-06-30T23:57:16.207200+00:00
  2. 2026-05-08 UNVERDICTED LOW v0.9.0 novelty 6.0
    37629 ms 5641 in 1542 out 2026-05-08T18:29:46.979513+00:00
  3. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 6.0
    29656 ms 5619 in 1159 out 2026-05-07T02:01:31.902080+00:00