Investigating Information Inconsistency in Multilingual Open-Domain Question Answering
This addresses potential retrieval bias and cultural influence in multilingual QA systems, which is an incremental analysis of existing datasets.
The study investigated information inconsistency in multilingual open-domain question answering systems, finding that retrieval models present different passages for the same question across languages, which may reflect cultural divergences and social biases.
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.