--- title: "M3TQA: Massively Multilingual Multitask Table Question Answering" description: "Translation runs through a six-stage pipeline built on GPT-4o and DeepSeek: structure-preserving initial… 2 references, cited by 2 papers here." authors: ["Daixin Shu", "Jian Yang", "Zhenhe Wu", "Xianjie Wu", "Xianfu Cheng", "Guan Xiangyuan", "Yanghai Wang", "Pengfei Wu", "Tingyang Yang", "Hualei Zhu", "Wei Zhang", "Ge Zhang", "Jiaheng Liu", "Zhoujun Li"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.1134/" doi: "10.18653/v1/2026.findings-acl.1134" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/shu-2026-m3tqa-massively-multilingual-multitask-table/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shu-2026-m3tqa-massively-multilingual-multitask-table/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/) / M3TQA: Massively Multilingual Multitask Table Question Answering # M3TQA: Massively Multilingual Multitask Table Question Answering **Authors:** Daixin Shu, [Jian Yang](https://md.research.elamur.ai/free/en/authors/jian-yang/), Zhenhe Wu, [Xianjie Wu](https://md.research.elamur.ai/free/en/authors/xianjie-wu/), Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, [Hualei Zhu](https://md.research.elamur.ai/free/en/authors/hualei-zhu/), [Wei Zhang](https://md.research.elamur.ai/free/en/authors/wei-zhang/), [Ge Zhang](https://md.research.elamur.ai/free/en/authors/ge-zhang/), [Jiaheng Liu](https://md.research.elamur.ai/free/en/authors/jiaheng-liu/) and [Zhoujun Li](https://md.research.elamur.ai/free/en/authors/zhoujun-li/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1134/) · [PDF](https://aclanthology.org/2026.findings-acl.1134.pdf) · [DOI 10.18653/v1/2026.findings-acl.1134](https://doi.org/10.18653/v1/2026.findings-acl.1134) · [OpenAlex](https://openalex.org/W7166891868) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/shu-2026-m3tqa-massively-multilingual-multitask-table/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary Research on table question answering with LLMs has focused mostly on English. The few multilingual table benchmarks that exist mainly cover Indo-European or otherwise prominent languages, and they are too small for fine-grained cross-lingual analysis. M3TQA addresses this gap. It starts from 50 real-world tables (41 Chinese, 9 English) that span four structural types and translates them into 97 languages from 12 language families. Translation runs through a six-stage pipeline built on GPT-4o and DeepSeek: - structure-preserving initial translation - filling in missed cells - refinement at the table level, then at the cell level - back-translation scored with a length-adaptive BLEU - a manual check From these tables the authors build two resources. M3TQA-Bench is a human-annotated test set with four task types. M3TQA-Instruct is an LLM-synthesised training set with no manual labels. Benchmarking more than 20 models reveals large performance gaps between language families. Fine-tuning on the unannotated synthetic data still yields clear gains, especially for low-resource languages. The work therefore provides both a broad evaluation resource and an inexpensive recipe for extending table reasoning beyond high-resource languages. ## Key points - **Translation quality:** After discarding roughly 10% of translations with low BLEU, 4,349 multilingual tables remain. Their median back-translation BLEU is 60.19 (minimum 34.06). Linguists' sample checks put cell-level accuracy above 93%. - **M3TQA-Bench:** 6,606 professionally annotated QA pairs, made up of 2,916 LLM-generated and 3,690 human-constructed pairs. - Tasks: numerical computation, cell extraction, factual verification and open-ended questions. - Native-speaker checks estimate annotation accuracy above 95%. - **M3TQA-Instruct:** 39,982 synthetic QA pairs. Numerical computation makes up over 70% of them (28,555), a skew the authors list as a limitation. - **Qwen3-8B ablation (average scores):** - Without thinking: 12.13 base, 28.36 with SFT, 35.06 with GRPO. - With thinking: 29.36 base, 39.54 with SFT, 45.17 with GRPO. - **Thinking mode vs. SFT:** Thinking mode helps Indo-European, Sino-Tibetan and Uralic languages more. SFT benefits Niger-Congo, Afro-Asiatic and Austronesian languages more. Because all source tables are Chinese or English, some cultural bias remains. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 65 works · 8,452 citations - [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 74 works · 7,814 citations 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works 🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works ## Cite Cite as: Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu and Zhoujun Li. 2026. M3TQA: Massively Multilingual Multitask Table Question Answering. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{shu2026m3tqa, title = {{M3TQA: Massively Multilingual Multitask Table Question Answering}}, author = {Daixin Shu, Jian Yang, Zhenhe Wu, Xianjie Wu, Xianfu Cheng, Guan Xiangyuan, Yanghai Wang, Pengfei Wu, Tingyang Yang, Hualei Zhu, Wei Zhang, Ge Zhang, Jiaheng Liu and Zhoujun Li}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.1134}, url = {https://doi.org/10.18653/v1/2026.findings-acl.1134} } ``` - [← previous LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose Models](https://md.research.elamur.ai/free/en/papers/mazor-2026-lvlm-aware-multimodal-retrieval-rag/) - [next → Machine learning and emoji prediction: How much accuracy can MARBERT achieve?](https://md.research.elamur.ai/free/en/papers/shormani-2026-machine-learning-emoji-prediction-much/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/) ## References 2 references, 2 of them with a card of ours. ↗ leads to the work. 1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, and 8 oth… — [Phi-4 Technical Report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/) 2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. *Updated 31 October 2026*