@inproceedings{ferreira-etal-2026-p3b3,
    title = "{P}3{B}3: A Multi-Turn Conversational Benchmark for Measuring {E}uropean and {B}razilian {P}ortuguese Variety Bias in {LLM}s",
    author = "Ferreira, Rafael  and
      Vieira, In{\^e}s  and
      Calvo, In{\^e}s  and
      Furtado, James  and
      Paulo, Iago  and
      Gl{\'o}ria-Silva, Diogo  and
      Tavares, Diogo  and
      Semedo, David  and
      Magalhaes, Joao",
    editor = "Huang, Kaiyu  and
      Mo, Fengran  and
      Chen, Pinzhen  and
      Jiang, Meng",
    booktitle = "Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models ({M}e{LLM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.mellm-1.23/",
    pages = "240--248",
    ISBN = "979-8-89176-430-9",
    abstract = "As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use. In Portuguese, European (pt-PT) and Brazilian (pt-BR) varieties remain unevenly represented, with pt-BR dominating in data quantity, while LLM preference for Portuguese variants remains underexplored.To address this gap, we introduce P3B3, an expert-curated variety agnostic benchmark of conversational prompts, along with an evaluation framework for measuring variety bias and controllability.Experiments on several models show that most LLMs exhibit a strong bias toward pt-BR, with variation in controllability across models. These results highlight the need for more balanced multilingual representation across language varieties."
}