@inproceedings{creanga-dinu-2024-designing,
    title = "Designing {NLP} Systems That Adapt to Diverse Worldviews",
    author = "Creanga, Claudiu  and
      Dinu, Liviu P.",
    editor = "Abercrombie, Gavin  and
      Basile, Valerio  and
      Bernadi, Davide  and
      Dudy, Shiran  and
      Frenda, Simona  and
      Havens, Lucy  and
      Tonelli, Sara",
    booktitle = "Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives) @ LREC-COLING 2024",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/author-page-diogo-silva-nova/2024.nlperspectives-1.10/",
    pages = "95--99",
    abstract = "Natural Language Inference (NLI) is foundational for evaluating language understanding in AI. However, progress has plateaued, with models failing on ambiguous examples and exhibiting poor generalization. We argue that this stems from disregarding the subjective nature of meaning, which is intrinsically tied to an individual{'}s \textit{weltanschauung} (which roughly translates to worldview). Existing NLP datasets often obscure this by aggregating labels or filtering out disagreement. We propose a perspectivist approach: building datasets that capture annotator demographics, values, and justifications for their labels. Such datasets would explicitly model diverse worldviews. Our initial experiments with a subset of the SBIC dataset demonstrate that even limited annotator metadata can improve model performance."
}