@inproceedings{loftus-etal-2025-using,
    title = "Using {LLM}s and Preference Optimization for Agreement-Aware {H}ate{W}i{C} Classification",
    author = {Loftus, Sebastian  and
      M{\"u}lthaler, Adrian  and
      Hoeken, Sanne  and
      Zarrie{\ss}, Sina  and
      Alacam, Ozge},
    editor = "Calabrese, Agostina  and
      de Kock, Christine  and
      Nozza, Debora  and
      Plaza-del-Arco, Flor Miriam  and
      Talat, Zeerak  and
      Vargas, Francielle",
    booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.woah-1.47/",
    pages = "538--547",
    ISBN = "979-8-89176-105-6",
    abstract = "Annotator disagreement poses a significant challenge in subjective tasks like hate speech detection. In this paper, we introduce a novel variant of the HateWiC task that explicitly models annotator agreement by estimating the proportion of annotators who classify the meaning of a term as hateful. To tackle this challenge, we explore the use of Llama 3 models fine-tuned through Direct Preference Optimization (DPO). Our experiments show that while LLMs perform well for majority-based hate classification, they struggle with the more complex agreement-aware task. DPO fine-tuning offers improvements, particularly when applied to instruction-tuned models. Yet, our results emphasize the need for improved modeling of subjectivity in hate classification and this study can serve as foundation for future advancements."
}