MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models 事件

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models arXiv:2606.01060v1 Announce Type: new Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally. Aligned systems still fail under jailbreaks, prompt injection, and retrieval-time corruption, suggesting behavior-level evaluation alone is incomplete. Post-training should leave measurable trac