@inproceedings{nghiem-etal-2026-smarter,
    title = "{SMARTER}: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models",
    author = "Nghiem, Huy  and
      Sachdeva, Advik  and
      Iii, Hal Daum{\textbackslash}'e",
    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.1584/",
    pages = "34306--34332",
    ISBN = "979-8-89176-390-6",
    abstract = "To address toxic content on social media, we introduce SMARTER, a data-efficient 2-stage framework for explainable content moderation using Large Language Models (LLMs). In Stage 1, we leverage LLMs' own outputs to generate synthetic explanations for correct and incorrect labels, enabling preference optimization with minimal supervision. In Stage 2, we refine explanation quality through cross-model training, allowing weaker models to align with stronger ones. Experiments on 3 benchmarks (HateXplain, Latent Hate, Implicit Hate) show SMARTER achieves up to 13{\%} macro-F1 improvement over few-shot baselines using only 6-57{\%} of training data. Our framework offers a scalable strategy for low-data settings by harnessing LLMs' self-improvement for explainable moderation."
}