@inproceedings{lucas-etal-2026-dia,
    title = "{DIA}-{HARM}: Dialectal Disparities in Harmful Content Detection Across 50 {E}nglish Dialects",
    author = "Lucas, Jason S  and
      White, Matt Murtagh  and
      Al-Lawati, Ali  and
      Uchendu, Uchendu  and
      Uchendu, Adaku  and
      Lee, Dongwon",
    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.144/",
    pages = "3171--3214",
    ISBN = "979-8-89176-390-6",
    abstract = "Harmful content detectors{---}particularly disinformation classifiers{---}are predominantly developed and evaluated on Standard American English (), leaving their robustness to dialectal variation unexplored. We present , the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE{'}s linguistically-grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of comprising 195K samples derived from established disinformation benchmarks. Our evaluation of 16 detection models reveals systematic vulnerabilities: human-written dialectal content degrades detection by 1.4{--}3.6{\%} F1, while AI-generated content remains stable. Fine-tuned transformers substantially outperform zero-shot LLMs (96.6{\%} vs. 78.3{\%} best-case F1), with some models exhibiting catastrophic failures exceeding 33{\%} degradation on mixed content. Cross-dialectal transfer analysis across 2,450 dialect pairs shows that multilingual models (mDeBERTa: 97.2{\%} average F1) generalize effectively, while monolingual models like RoBERTa and XLM-RoBERTa fail on dialectal inputs. These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non- speakers worldwide. We release the benchmark, including the , and evaluation tools."
}