Papers
arxiv:2509.04111

MultiWikiQA: A Reading Comprehension Benchmark in 300+ Languages

Published on Sep 4
Authors:

Abstract

A new multilingual reading comprehension dataset, MultiWikiQA, is introduced, featuring questions generated by LLMs and evaluated for quality across 30 languages, demonstrating significant performance differences among models and languages.

AI-generated summary

We introduce a new reading comprehension dataset, dubbed MultiWikiQA, which covers 306 languages. The context data comes from Wikipedia articles, with questions generated by an LLM and the answers appearing verbatim in the Wikipedia articles. We conduct a crowdsourced human evaluation of the fluency of the generated questions across 30 of the languages, providing evidence that the questions are of good quality. We evaluate 6 different language models, both decoder and encoder models of varying sizes, showing that the benchmark is sufficiently difficult and that there is a large performance discrepancy amongst the languages. The dataset and survey evaluations are freely available.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.04111 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.04111 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.