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

Source: [Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering](<https://www.sota2.com/research/paper/68fa7c191e209131cea8c501>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:56:14.357Z

Authors: Lorena Calvo-Bartolom\\'e, Val\\'erie Aldana, Karla Cantarero, Alonso Madro\\~nal de Mesa, Jer\\'onimo Arenas-Garc\\'ia, Jordan Boyd-Graber

Published: 2025-10-13T20:48:26.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.11928>)

[PDF](<https://arxiv.org/pdf/2510.11928.pdf>)