@inproceedings{hoblitzell-2026-beyond,
    title = "Beyond Hallucination: Reframing {LLM} Quality Assessment as Task-Output Alignment",
    author = "Hoblitzell, Andrew",
    editor = "Elazar, Yanai  and
      Ettinger, Allyson  and
      Kassner, Nora  and
      Ruder, Sebastian",
    booktitle = "Proceedings of The Big Picture v2: Crafting a Research Narrative",
    month = jul,
    year = "2026",
    address = "San Diego, CA, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bigpicture-main.3/",
    pages = "22--30",
    ISBN = "979-8-89176-416-3",
    abstract = "Current hallucination detection systems operate under a flawed assumption: that model outputs deviating from factual grounding are uniformly problematic regardless of task context, modality, or cultural setting. Through analysis of computational humor as a motivating case study, we demonstrate that identical model behaviors require radically different evaluations depending on context. We propose reframing hallucination detection as task-output alignment assessment, introducing a three-dimensional framework spanning factual grounding requirements, novelty requirements, and risk tolerance."
}