@inproceedings{minegishi-etal-2026-understanding,
    title = "Understanding Emergent Misalignment via Feature Superposition Geometry",
    author = "Minegishi, Gouki  and
      Furuta, Hiroki  and
      Kojima, Takeshi  and
      Iwasawa, Yusuke  and
      Matsuo, Yutaka",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1402/",
    pages = "30385--30414",
    ISBN = "979-8-89176-390-6",
    abstract = "Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, its underlying mechanism remains unclear. To uncover the reason behind this phenomenon, we propose a mechanistic account based on the geometry of feature superposition. Because features are encoded in overlapping, fine-tuning that amplifies a target feature also unintentionally strengthens nearby harmful features in accordance with their similarity. We give a simple gradient-level derivation of this mechanism and empirically test it across multiple LLMs (Gemma-2 2B/9B/27B, LLaMA-3.1 8B, gpt-oss 20B). Using sparse autoencoders (SAEs), we identify features tied to misalignment-inducing data and to harmful behaviors, and show that they are geometrically closer to each other than features derived from non-inducing data. This trend generalizes across domains (e.g., health, career, legal advice). Finally, we show that a geometry-aware approach{---}filtering training samples nearest to toxic features{---}reduces misalignment by 34.5{\%}, substantially outperforming random removal and achieving stronger mitigation than LLM-as-a-judge{--}based filtering. Our study explains emergent misalignment through feature superposition, providing a basis for understanding and mitigating this phenomenon."
}