Suppressing Misaligned Behaviors in Language Models, Durably

arXiv:2611.05358 · cs.CL, cs.AI, cs.LG · Submitted 2026-11-03 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-11-03

Updated: 2026-11-03

Code: https://github.com/pat-jj/pearl

Terminology

Sources

Related papers