M3TQA: Massively Multilingual Multitask Table Question Answering

Tabular data is a fundamental component of real-world information systems. However, existing multilingual table benchmarks suffer from geolinguistic imbalance -overrepresenting certain languages and lacking sufficient scale for rigorous cross-lingual analysis. To address these limitations, we introduce M 3 TQA, which is a comprehensive framework for massively multilingual multitask table question answering, including subsequent datasets M 3 TQA-BENCH and M 3 TQA-INSTRUCT, featuring tables expanded to 97 languages from Chinese and English sources. M 3 TQA-BENCH includes 6,606 professionally annotated question-answering pairs across four tasks designed to evaluate nuanced table reasoning capabilities. Additionally, we synthesized the training set M 3 TQA-INSTRUCT in 97 languages using Large Language Model (LLM). Experiments on state-of-the-art LLMs reveal critical insights into cross-lingual generalization, demonstrating that synthetically generated, unannotated training data can significantly boost performance, particularly for lowresource languages. M 3 TQA establishes a new standard for multilingual table understanding, providing both a challenging evaluation platform and a scalable methodology for future research. The dataset and code are available at https://m3tqa.github.io.