MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering
Jui-I Wang, Hen-Hsen Huang, Hsin-Hsi Chen
Abstract
We introduce MESAQA, a novel dataset focusing on multi-span contextual understanding question answering (QA).Unlike traditional single-span QA systems, questions in our dataset consider information from multiple spans within the context document. MESAQA supports evidence-grounded QA, demanding the model’s capability of answer generation and multi-evidence identification. Our automated dataset creation method leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans. Experimental results show that current models struggle with multi-span contextual QA, underscoring the need for new approaches. Our dataset sets a benchmark for this emerging QA paradigm, promoting research in complex information retrieval and synthesis.
BibTeX
@inproceedings{wang-etal-2025-mesaqa,
title = "{MESAQA}: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering",
author = "Wang, Jui-I and
Huang, Hen-Hsen and
Chen, Hsin-Hsi",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.724/",
pages = "10891--10901"
}