The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs.

arXiv:2511.20104v2 Announce Type: replace-cross Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested m