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

This research was completed in context of the LASR Labs Fellowship Summer 2026, by Ardy Haroen, Florian Lorkowski and Samuel Nellessen. The team was mentored by Felix Hostätter. Find out more about the programme and express interest in upcoming cohorts at lasrlabs.org. The full paper is available on arXiv.TL;DR: We present a method to detect alignment faking in LLMs, that does not require chain-of-thought monitorability, highly realistic evaluations or mechanistic interventions. We do so by conv...