@inproceedings{deas-etal-2026-characterizing,
    title = "Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models",
    author = "Deas, Nicholas  and
      Mejia, Ivan Ernesto Perez  and
      Yang, Ellie  and
      McKeown, Kathleen",
    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.2188/",
    pages = "47272--47294",
    ISBN = "979-8-89176-390-6",
    abstract = "Prior work evaluating emotion and affective understanding in large language models (LLMs) typically rely on predetermined label sets or focus on a singular evaluation task (e.g., emotion detection). We consider affective states, referring to the much broader variety of terms people use to label their emotional experiences. We evaluate multilingual language models' understanding of affective states in English and Spanish through three different tasks: 1) {\_}identification{\_}, where models predict an affective state given text, 2) {\_}expression{\_}, where models generate text expressing a given affective state, and 3) {\_}verification{\_}, where models report whether a given term refers to an affective state. We show that performance on one task is not necessarily predictive of performance on another. Using these three tasks, we then begin to explore when and why models struggle to understand particular affective states compared to others. We examine systematic patterns in the affective state terms that are well and poorly understood by models, characterizing the working emotion vocabulary of LLMs."
}