Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Calvo-Bartolomé, Lorena, Aldana, Valérie, Cantarero, Karla, de Mesa, Alonso Madroñal, Arenas-García, Jerónimo, Boyd-Graber, Jordan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909843764281344
author Calvo-Bartolomé, Lorena
Aldana, Valérie
Cantarero, Karla
de Mesa, Alonso Madroñal
Arenas-García, Jerónimo
Boyd-Graber, Jordan
author_facet Calvo-Bartolomé, Lorena
Aldana, Valérie
Cantarero, Karla
de Mesa, Alonso Madroñal
Arenas-García, Jerónimo
Boyd-Graber, Jordan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering
Calvo-Bartolomé, Lorena
Aldana, Valérie
Cantarero, Karla
de Mesa, Alonso Madroñal
Arenas-García, Jerónimo
Boyd-Graber, Jordan
Computation and Language
Artificial Intelligence
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.
title Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.11928