Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning

arXiv cs.AIOctober 27, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2610.33180v1 Announce Type: new Abstract: Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour. Misaligned and evaluation-aware models might engage in alignment faking, where they pursue a hidden goal, but conceal this behaviour when they suspect effective oversight such as during training, evaluation or audited deployment. Such a model might view any prompt-based intervention that aims to reveal latent propensities as part of the evaluation, calling into question the reliability of existing alignment evaluations. Current methods for detecting alignment faking rely on chain-of-thought monitorability, highly realistic environme

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Företag