Multilingual question answering (QA) systems must ensure factual consistency across languages, especially for objective queries such as What is jaundice?, while also accounting for cultural variation in subjective responses. We propose MIND, a user-in-the-loop fact-checking pipeline to detect factual and cultural discrepancies in multilingual QA knowledge bases. MIND highlights divergent answers to culturally sensitive questions (e.g., Who assists in childbirth?) that vary by region and context. We evaluate MIND on a bilingual QA system in the maternal and infant health domain and release a dataset of bilingual questions annotated for factual and cultural inconsistencies. We further test MIND on datasets from other domains to assess generalization. In all cases, MIND reliably identifies inconsistencies, supporting the development of more culturally aware and factually consistent QA systems.
Cite
@article{arxiv.2510.11928,
title = {Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering},
author = {Lorena Calvo-Bartolomé and Valérie Aldana and Karla Cantarero and Alonso Madroñal de Mesa and Jerónimo Arenas-García and Jordan Boyd-Graber},
journal= {arXiv preprint arXiv:2510.11928},
year = {2025}
}