@inproceedings{gupta-etal-2025-endive,
    title = "{E}n{D}ive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models",
    author = "Gupta, Abhay  and
      Cheung, Jacob  and
      Meng, Philip  and
      Sayyed, Shayan  and
      Zhu, Kevin  and
      Liao, Austen  and
      O{'}Brien, Sean",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.913/",
    doi = "10.18653/v1/2025.findings-emnlp.913",
    pages = "16830--16855",
    ISBN = "979-8-89176-335-7",
    abstract = "The diversity of human language, shaped by social, cultural, and regional influences, presents significant challenges for natural language processing (NLP) systems. Existing benchmarks often overlook intra-language variations, leaving speakers of non-standard dialects underserved. To address this gap, we introduce EnDive (English Diversity), a benchmark that evaluates seven state-of-the-art (SOTA) large language models (LLMs) across tasks in language understanding, algorithmic reasoning, mathematics, and logic. Our framework translates Standard American English datasets into five underrepresented dialects using few-shot prompting with verified examples from native speakers, and compares these translations against rule-based methods via fluency assessments, preference tests, and semantic similarity metrics. Human evaluations confirm high translation quality, with average scores of at least 6.02/7 for faithfulness, fluency, and formality. By filtering out near-identical translations, we create a challenging dataset that reveals significant performance disparities{---}models consistently underperform on dialectal inputs compared to Standard American English (SAE). EnDive thus advances dialect-aware NLP by uncovering model biases and promoting more equitable language technologies."
}