Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment

arXiv:2605.12798v2 Announce Type: replace-cross Abstract: Post-training a language model can induce surprising behavioral changes far beyond the intended training target. We study two particularly striking examples: emergent misalignment (EM), where fine-tuning on a narrow dataset leads to misaligned behavior in unrelated contexts, and subliminal learning (SL), where a student model inherits a teacher's misalignment through seemingly benign training data. We examine how the training data, evaluation data, and training method shape where and how strongly misalignment transfers between data and

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.