Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning
This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.
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…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-27 04:00 · arXiv cs.AI
Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning