Elamur Research⌕
☰
home / papers / 2026 / ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning

Paper · 2026 · Zhensheng Wang, Xiaole Liu, Wenmian Yang et al.

Summary

Most LLM-based tabular QA systems only look backward: they retrieve and compute over stored records but cannot answer questions about future values. The authors define a new task, open-domain tabular QA for future forecasting and reasoning, and release ODTQA-FoRe, a benchmark built from Chinese real estate sales data covering 2022–2024. A system must find the right tables in a pool, pull historical series via SQL, predict 2024 values that are withheld from inference, and then answer either direct forecasting questions or comparative questions that depend on those forecasts. As a baseline, they propose TimeFore, an agent framework with three roles. A Retriever writes SQL, a Forecaster calls dedicated time-series models instead of relying on the LLM, and an Analyzer produces standardized answers. Across five open LLMs, TimeFore clearly beats a BM25 plus five-shot prompting baseline on both forecasting error and reasoning accuracy. Ablations show that forecast quality is the main bottleneck. The work matters because it offers the first resource for evaluating forward-looking numerical QA over structured data.

Key points

  • ODTQA-FoRe has 28,507 QA pairs: 8,042 time-series forecasting and 20,465 forecast-based reasoning questions. They cover 10 Chinese cities, drawn from a 288-table pool averaging about 845 rows per table.
  • Data construction:
    • The source is the RETQA data, extended with Tianjin and Chengdu.
    • 60,183 projects were filtered down to 11,149.
    • The data is split by project in a 6:2:2 ratio (6,562 / 2,278 / 2,309 projects).
    • 31 Dec 2023 is the cutoff separating history (2022–2023) from future ground truth (2024).
  • TimeFore has three agents: Retriever (table selection plus SQL), Forecaster (external time-series model) and Analyzer (answer synthesis).
  • Results:
    • Models tested: Qwen3 30B A3B, Qwen3 Next 80B A3B Thinking, GPT-OSS 20B/120B and GLM 4.5 Air.
    • Example gains: Qwen3 30B reasoning accuracy rose from 12.19 to 31.59, and GPT-OSS 120B forecasting MRE fell from 0.1683 to 0.1151.
    • GLM 4.5 Air achieved the best reasoning F1 (61.24).
  • Ablation:
    • Supplying gold table captions or gold history helps only slightly.
    • Supplying gold future values yields the largest jump, so forecasting accuracy is the key limitation.

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

🎓Beijing Normal UniversityBeijing · China22 works · 3,177 citations🎓Beijing Normal-Hong Kong Baptist UniversityZhuhai · China5 works · 536 citations🎓Beijing Normal University, ZhuhaiZhuhai · China4 works

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 worksComputer Networks and Communications · 100 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,685 worksQuestion answering · 487 works

Cite

Cite as Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang and Weijia Jia. 2026. ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.347

@inproceedings{wang2026odtqa,
  title = {{ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning}},
  author = {Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang and Weijia Jia},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.347},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.347}
}

References

38 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, and 1 others. 2025. gpt-oss-120b & gpt-oss-20b model card. Preprint, arXiv:2508.10925. \#\# Acknowledgments This work is supported in part by the National Natural Science F…
  2. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. Reading wikipedia to answer open-domain questions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 -August 4, Volume 1: Long Papers, pages 1870–1879. Assoc…
  3. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025b. Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. CoRR, abs/2503.09567.
  4. Ziyang Chen, Jinzhi Liao, and Xiang Zhao. 2023. Multi-granularity temporal question answering over knowledge graphs. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 11378–11392. Asso… find
  5. An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang, and Sifei Liu. 2024. Spatialrgpt: Grounded spatial reasoning in vision-language models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, N… find
  6. Lizhi Cheng, Wenmian Yang, and Weijia Jia. 2023. A scope sensitive and result attentive model for multi-intent spoken language understanding. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2… find
  7. Xi Fang, Weijie Xu, Fiona Anting Tan, Jiani Zhang, Ziqing Hu, Yanjun (Jane) Qi, Scott Nickleach, Diego Socolinsky, "SHS" Srinivasan Sengamedu, and Christos Faloutsos. 2024. Large language models (llms) on tabular data: Prediction, generation, and understanding — a survey. Transactions on Machine Lea… find
  8. Nate Gruver, Marc Finzi, Shikai Qiu, and Andrew Gordon Wilson. 2023a. Large language models are zero-shot time series forecasters. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10…
  9. Nate Gruver, Marc Finzi, Shikai Qiu, and Andrew Gordon Wilson. 2023b. Large language models are zero-shot time series forecasters. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10…
  10. Jonathan Herzig, Thomas Müller, Syrine Krichene, and Julian Martin Eisenschlos. 2021. Open domain question answering over tables via dense retrieval. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAA…
  11. Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, and Mingsheng Long. 2024a. itransformer: Inverted transformers are effective for time series forecasting. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.ne… find
  12. Yong Liu, Guo Qin, Xiangdong Huang, Jianmin Wang, and Mingsheng Long. 2024b. Autotimes: Autoregressive time series forecasters via large language models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,… find
  13. Md Mahmuddun Nabi Murad, Mehmet Aktukmak, and Yasin Yilmaz. 2025. Wpmixer: Efficient multi-resolution mixing for long-term time series forecasting. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, pages 19581… find
  14. Panupong Pasupat and Percy Liang. 2015. Compositional semantic parsing on semi-structured tables. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1470–…
  15. Kezhi Kong, Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Chuan Lei, Christos Faloutsos, Huzefa Rangwala, and George Karypis. 2024. Opentab: Advancing large language models as open-domain table reasoners. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vien… find
  16. Libo Qin, Qiguang Chen, Jingxuan Zhou, Jin Wang, Hao Fei, Wanxiang Che, and Min Li. 2025. Divide-solve-combine: An interpretable and accurate prompting framework for zero-shot multi-intent detection. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25… find
  17. Sunjun Kweon, Yeonsu Kwon, Seonhee Cho, Yohan Jo, and Edward Choi. 2023. Open-wikitable : Dataset for open domain question answering with complex reasoning over table. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 8285–8297. Associati… find
  18. Stephen E Robertson and Steve Walker. 1994. Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval. In SI-GIR’94: Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, organised by Dubl… find
  19. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Proc…
  20. Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, and Ming Jin. 2025. Time-moe: Billion-scale time series foundation models with mixture of experts. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  21. Xiaobo Liang, Wenjin Xie, Juntao Li, Wanfu Wang, Yibin Chen, Kehai Chen, and Min Zhang. 2025. Tool learning via inference-time scaling and cycle verifier. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, Findings of ACL, pages 24658–2… find
  22. Michael Stonebraker, Lawrence A. Rowe, and Michael Hirohama. 2019. The implementation of POST-GRES. In Michael L. Brodie, editor, Making Databases Work: the Pragmatic Wisdom of Michael Stonebraker, volume 22 of ACM Books, pages 519– 559. ACM / Morgan & Claypool. find
  23. Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, and Tom Hartvigsen. 2024. Are language models actually useful for time series forecasting? find
  24. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. find
  25. Cunxiang Wang, Sirui Cheng, Qipeng Guo, Yuanhao Yue, Bowen Ding, Zhikun Xu, Yidong Wang, Xiangkun Hu, Zheng Zhang, and Yue Zhang. 2023. Evaluating open-qa evaluation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 202… find
  26. Shiyu Wang, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y. Zhang, and Jun Zhou. 2024a. Timemixer: Decomposable multiscale mixing for time series forecasting. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenRevie… find
  27. Yuxiang Wang, Jianzhong Qi, and Junhao Gan. 2025a. Accurate and regret-aware numerical problem solver for tabular question answering. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, pages 12775–12783. AAAI P… find
  28. Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Guo Qin, Haoran Zhang, Yong Liu, Yunzhong Qiu, Jianmin Wang, and Mingsheng Long. 2024b. Timexer: Empowering transformers for time series forecasting with exogenous variables. Advances in Neural Information Processing Systems, 37:469–498. find
  29. Zhensheng Wang, Wenmian Yang, Kun Zhou, Yiquan Zhang, and Weijia Jia. 2025b. RETQA: A large-scale open-domain tabular question answering dataset for real estate sector. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia,… find
  30. Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2023. Timesnet: Temporal 2d-variation modeling for general time series analysis. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. find
  31. Bowen Xing, Libo Qin, Zhihong Zhu, Zhou Yu, and Ivor W Tsang. 2025. Dxa-net: Dual-task cross-lingual alignment network for zero-shot cross-lingual spoken language understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence. find
  32. Jiahuan Yan, Bo Zheng, Hongxia Xu, Yiheng Zhu, Danny Z. Chen, Jimeng Sun, Jian Wu, and Jintai Chen. 2024. Making pre-trained language models great on tabular prediction. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Review.net. find
  33. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  34. Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, and Liang He. 2025. Optimizing question semantic space for dynamic retrieval-augmented multi-hop question answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17814– 17… find
  35. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir R. Radev. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Proceedings of the 20…
  36. Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, Mingdao Liu, Rui Lu, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yao Wei, Yean Cheng, and 80 others. 2025a. GLM-4.5: agentic, reasoning, and coding (ARC) fo…
  37. Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Jinpeng Wang, Zaiyuan Wang, Yang Yang, Lingyue Yin, Mingren Yin, Zhenwei Zhu, Tianle Cai, Zehui Chen, Jiecao Chen, Yantao Du, Xiang Gao, Jiacheng Guo, Liang Hu, Jianpeng Jiao, and 11 others. 2025b. Futurex: An advanced live benchmark for… — [arXiv:2508.11987](https://arxiv.org/abs/2508.11987) find
  38. Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, and Wanxiang Che. 2025. A survey of table reasoning with large language models. Frontiers Comput. Sci., 19(9):199348. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-odtqa-fore-open-domain-tabular/