@inproceedings{nhan-thin-2026-gradient,
    title = "Gradient Descenders at {S}em{E}val-2026 Task 9: Data-Centric Counterfactual Augmentation for Multi-Label Hate Speech Detection",
    author = "Nhan, Tran  and
      Thin, Dang",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.113/",
    pages = "811--820",
    ISBN = "979-8-89176-414-9",
    abstract = "In this paper, we describe the Gradient Descenders submission to SemEval-2026 Task 9 Subtask 2: Multi-Label Hate Speech Detection. Existing Transformer-based approaches often exhibit degraded performance on this task due to severe class imbalance and complex class intersectionality, leading to the learning of spurious correlations. To counteract this, we introduce a novel, data-centric counterfactual augmentation pipeline. We employ Large Language Models (LLMs) as semantic generators to synthesize diverse, targeted training samples via three distinct prompting strategies: Additive Label-Flipping (Attribute Injection), Context Decoupling, and Cross-Domain Identity Substitution. Fine-tuning a RoBERTa classifier on this augmented corpus significantly improves the model{'}s sensitivity to minority classes. Ultimately, our system achieves a Macro-F1 score of 44.15{\textbackslash}{\%} on the official test set, highlighting the efficacy of targeted LLM-based augmentation in highly imbalanced, multi-label environments."
}