@inproceedings{wang-etal-2026-languages,
    title = "All Languages Matter: Understanding and Mitigating Language Bias in Multilingual {RAG}",
    author = "Wang, Dan  and
      Mo, Guozhao  and
      Shi, Yafei  and
      Zhang, Cheng  and
      Zheng, Bo  and
      Cao, Boxi  and
      Chen, Xuanang  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      He, Ben  and
      Han, Xianpei  and
      Sun, Le",
    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.338/",
    pages = "7441--7455",
    ISBN = "979-8-89176-390-6",
    abstract = "Multilingual Retrieval-Augmented Generation (mRAG) leverages cross-lingual evidence to ground Large Language Models (LLMs) in global knowledge. However, we show that current mRAG systems suffer from a language bias during reranking, systematically favoring English and the query{'}s native language. By introducing an estimated oracle evidence analysis, we quantify a substantial performance gap between existing rerankers and the achievable upper bound. Further analysis reveals a critical distributional mismatch: while optimal predictions require evidence scattered across multiple languages, current systems systematically suppress such ``answer-critical'' documents, thereby limiting downstream generation performance. To bridge this gap, we propose \textit{\textbf{L}anguage-\textbf{A}gnostic \textbf{U}tility-driven \textbf{R}eranker \textbf{A}lignment (LAURA)}, Experiments across diverse languages and generation models show that LAURA effectively mitigates language bias and consistently improves mRAG performance."
}