# Investigating Information Inconsistency in Multilingual Open-Domain Question Answering

Source: [Investigating Information Inconsistency in Multilingual Open-Domain Question Answering](<https://www.sota2.com/research/paper/68fa6ca41e209131cea352a0>)

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

Data updated: 2025-10-26T00:15:46.115Z

Authors: Shramay Palta, Haozhe An, Yifan Yang, Shuaiyi Huang, Maharshi Gor

Published: 2022-05-25T02:58:54.000Z

## Abstract

Retrieval based open-domain QA systems use retrieved documents and answer-span selection over retrieved documents to find best-answer candidates. We hypothesize that multilingual Question Answering (QA) systems are prone to information inconsistency when it comes to documents written in different languages, because these documents tend to provide a model with varying information about the same topic. To understand the effects of the biased availability of information and cultural influence, we analyze the behavior of multilingual open-domain question answering models with a focus on retrieval bias. We analyze if different retriever models present different passages given the same question in different languages on TyDi QA and XOR-TyDi QA, two multilingualQA datasets. We speculate that the content differences in documents across languages might reflect cultural divergences and/or social biases.

## 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/2205.12456>)

[PDF](<https://arxiv.org/pdf/2205.12456.pdf>)