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

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 hidde