arxiv
PublishedApril 24, 2026 at 4:00 AM
—neutral
Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
Publisher summary· verbatim
arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited. Prior di
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivFrom Local to Cluster: A Unified Framework for Causal Discovery with Latent Variables10harxivConsequentialist Objectives and Catastrophe10harxivEgoMAGIC- An Egocentric Video Field Medicine Dataset for Training Perception Algorithms10harxivA general optimization solver based on OP-to-MaxSAT reduction10hOriginally published on arxiv ↗