Elamur Research⌕
☰
home / papers / 2026 / When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

Paper · 2026 · Shenghao Ye, Yu Guo, Dong Jin et al.

Summary

This paper addresses how large language models lose accuracy in table question answering (TableQA) when questions are complex and tables are large. In that setting, both inputs carry noise. Questions can contain phrases that look like constraints but have no matching data in the table, and most rows in a big table are irrelevant to the answer. The authors argue that robust TableQA needs two abilities: Relevance Filtering and Table Pruning. They propose EnoTab, a two-stage framework built on both.

  • Evidence-based Question Denoising splits the question into minimal semantic units called evidences. It keeps only those that recur across repeated LLM generations and can be grounded in actual table content.
  • Evidence Tree-guided Table Denoising turns the retained evidences into a logical tree that prunes the table step by step. Each intermediate state can be inspected. A post-order rollback undoes steps that would wrongly discard answer-relevant rows.

The authors report strong results on large-table benchmarks. Smaller tables are not over-pruned. This makes LLM-based TableQA more transparent and dependable on realistic, noisy data.

Key points

  • Evidences are structured as (column, data type, condition) triples, such as a district or population constraint. They are combined with AND/OR logic into an Evidence Tree.
  • Evidence relevance rests on two criteria: consistency across K=5 generation rounds, and usability, meaning matching data exists in the table.
  • In one motivating example, only 3 of 260 rows were needed to answer the question, and pruning to that 3-row subtable fixed the model's error.
  • Evaluation covers STQA-L and STQA-N (large-scale tables) and WikiTQ and TabFact (smaller tables). The framework uses GPT-4o, GPT-4o-mini, Qwen-1.5 and Llama-2.
  • Stated limitations:
    • Testing covers only single-table QA.
    • Validation struggles with special cell formats such as win–loss scores like "1-1".

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

🎓The University of MelbourneMelbourne · Australia100 works · 22,618 citations🎓University of Science and Technology of ChinaHefei · China108 works · 112,698 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, Jianyang and Xiaofeng Jiang. 2026. When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1102

@inproceedings{ye2026when,
  title = {{When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables}},
  author = {Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, Jianyang and Xiaofeng Jiang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1102},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1102}
}

References

46 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, and Vivek Gupta. 2025. Weaver: Interweaving sql and llm for table reasoning. arXiv preprint arXiv:2505.18961.
  2. Nikhil Abhyankar, Vivek Gupta, Dan Roth, and Chandan K Reddy. 2025. H-star: Llm-driven hybrid sql-text adaptive reasoning on tables. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: L… find
  3. Shengnan An, Xunliang Cai, Xuezhi Cao, Xiaoyu Li, Yehao Lin, Junlin Liu, Xinxuan Lv, Dan Ma, Xuanlin Wang, Ziwen Wang, et al. 2025. Amo-bench: Large language models still struggle in high school math competitions. arXiv preprint arXiv:2510.26768. find
  4. Michael J Cafarella, Alon Halevy, Daisy Zhe Wang, Eugene Wu, and Yang Zhang. 2008. Webtables: ex-Mike Lewis. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.
  5. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
  6. Honglin Lin, Zheng Liu, Yun Zhu, Chonghan Qin, Juekai Lin, Xiaoran Shang, Conghui He, Wentao Zhang, and Lijun Wu. 2026a. Mmfinereason: Closing the multimodal reasoning gap via open data-centric methods. arXiv preprint arXiv:2601.21821. — [arXiv:2601.21821](https://arxiv.org/abs/2601.21821) find
  7. Honglin Lin, Chonghan Qin, Zheng Liu, Qizhi Pei, Yu Li, Zhanping Zhong, Xin Gao, Yanfeng Wang, Conghui He, and Lijun Wu. 2026b. Scientific image synthesis: Benchmarking, methodologies, and downstream utility. arXiv preprint arXiv:2601.17027. — [arXiv:2601.17027](https://arxiv.org/abs/2601.17027) find
  8. Xin Lin, Zhenya Huang, Zhiqiang Zhang, Jun Zhou, and Enhong Chen. 2025. Explore what llm does not know in complex question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24585–24594. find
  9. Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, and Jian-Guang Lou. 2021. Tapex: Table pre-training via learning a neural sql executor. arXiv preprint arXiv:2107.07653.
  10. Zheng Liu, Hao Liang, Xijie Huang, Wentao Xiong, Qinhan Yu, Linzhuang Sun, Chong Chen, Conghui He, Bin Cui, and Wentao Zhang. 2024. Syn-thvlm: High-efficiency and high-quality synthetic data for vision language models. arXiv preprint arXiv:2407.20756, 3. — [arXiv:2407.20756](https://arxiv.org/abs/2407.20756) find
  11. Zheng Liu, Honglin Lin, Chonghan Qin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, et al. 2026. Chart-verse: Scaling chart reasoning via reliable programmatic synthesis from scratch. arXiv preprint arXiv:2601.13606. — [arXiv:2601.13606](https://arxiv.org/abs/2601.13606) find
  12. Zheng Liu, Mengjie Liu, Jingzhou Chen, Jingwei Xu, Bin Cui, Conghui He, and Wentao Zhang. 2025a. Fusion: Fully integration of vision-language representations for deep cross-modal understanding. arXiv preprint arXiv:2504.09925. — [arXiv:2504.09925](https://arxiv.org/abs/2504.09925) find
  13. Zheng Liu, Mengjie Liu, Siwei Wen, Mengzhang Cai, Bin Cui, Conghui He, and Wentao Zhang. 2025b. From uniform to heterogeneous: Tailoring policy optimization to every token’s nature. arXiv preprint arXiv:2509.16591. — [arXiv:2509.16591](https://arxiv.org/abs/2509.16591) find
  14. Qingyang Mao, Qi Liu, Zhi Li, Mingyue Cheng, Zheng Zhang, and Rui Li. 2024. Potable: Programming standardly on table-based reasoning like a human analyst. arXiv preprint arXiv:2412.04272. — [arXiv:2412.04272](https://arxiv.org/abs/2412.04272) find
  15. Md Nahid and Davood Rafiei. 2024a. Normtab: Improving symbolic reasoning in llms through tabular data normalization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3569–3585. find
  16. Md Nahid and Davood Rafiei. 2024b. Tabsqlify: Enhancing reasoning capabilities of llms through table decomposition. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5725–57… find
  17. Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Hailey Schoelkopf, Riley Kong, Xiangru Tang, et al. 2022. Fetaqa: Free-form table question answering.
  18. Transactions of the Association for Computational Linguistics, 10:35–49. find
  19. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2024. Gpt-4 technical report.
  20. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
  21. Panupong Pasupat and Percy Liang. 2015. Compositional semantic parsing on semi-structured tables. arXiv preprint arXiv:1508.00305.
  22. Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan O Arik. 2024. Chase-sql: Multi-path reasoning and preference optimized candidate selection in text-to-sql. arXiv preprint arXiv:2410.01943. — [arXiv:2410.01943](https://arxiv.org/abs/2410.01943) find
  23. Nitarshan Rajkumar, Raymond Li, and Dzmitry Bahdanau. 2022. Evaluating the text-to-sql capabilities of large language models. arXiv preprint arXiv:2204.00498. find
  24. Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han, and Dongmei Zhang. 2024. Table meets llm: Can large language models understand structured table data? a benchmark and empirical study. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 645–654. find
  25. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, et al. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295. find
  26. Lihan Wang, Bowen Qin, Binyuan Hui, Bowen Li, Min Yang, Bailin Wang, Binhua Li, Jian Sun, Fei Huang, Luo Si, et al. 2022a. Proton: Probing schema linking information from pre-trained language models for text-to-sql parsing. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and… find
  27. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022b. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171.
  28. Yuxiang Wang, Junhao Gan, and Jianzhong Qi. 2025a. Tabsd: Large free-form table question answering with sql-based table decomposition. arXiv preprint arXiv:2502.13422. — [arXiv:2502.13422](https://arxiv.org/abs/2502.13422) find
  29. Yuxiang Wang, Jianzhong Qi, and Junhao Gan. 2025b. Accurate and regret-aware numerical problem solver for tabular question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 12775–12783. find
  30. Zilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, and Tomas Pfister. 2024. Chain-of-table: Evolving tables in the reasoning chain for table understanding. ICLR. find
  31. Fei Wu, Zhenrong Zhang, Qikai Chang, Jianshu Zhang, Quan Liu, and Jun Du. 2026. Step potential advantage estimation: Harnessing intermediate confidence and correctness for efficient mathematical reasoning. arXiv preprint arXiv:2601.03823.
  32. Zhenhe Wu, Zhongqiu Li, Mengxiang Li, Jie Zhang, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Yongxiang Li, Zhoujun Li, et al. 2025a. Mr-sql: multi-level retrieval enhances inference for llm in text-to-sql. In International Conference on Database Systems for Advanced Applications, pages 403–413. S… find
  33. Zhenhe Wu, Zhongqiu Li, Jie Zhang, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Bing Wang, Hongyan Xie, Shuangyong Song, and Zhoujun Li. 2025b. UCS-SQL: Uniting content and structure for enhanced semantic bridging in text-to-SQL. In Findings of the Association for Computational Linguistics: ACL 20… find
  34. Zhenhe Wu, Jian Yang, Jiaheng Liu, Xianjie Wu, Changzai Pan, Jie Zhang, Yu Zhao, Shuangyong Song, Yongxiang Li, and Zhoujun Li. 2025c. Tabler1: Region-based reinforcement learning for table understanding. arXiv preprint arXiv:2505.12415. — [arXiv:2505.12415](https://arxiv.org/abs/2505.12415) find
  35. Zirui Wu and Yansong Feng. 2024. Protrix: Building models for planning and reasoning over tables with sentence context. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4378–4406. find
  36. Yunhu Ye, Binyuan Hui, Min Yang, Binhua Li, Fei Huang, and Yongbin Li. 2023. Large language models are versatile decomposers: Decomposing evidence and questions for table-based reasoning. In Proceedings of the 46th international ACM SIGIR conference on research and development in information retriev… find
  37. Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. Tabert: Pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:2005.08314.
  38. Peiying Yu, Guoxin Chen, and Jingjing Wang. 2025. Table-critic: A multi-agent framework for collaborative criticism and refinement in table reasoning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17432–17451, Vienna, Austri…
  39. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Proceedings of the 2018 Conference on Empirical Me…
  40. Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, and Yongbin Li. 2026. Expseek: Self-triggered experience seeking for web agents.
  41. Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, and Wanxiang Che. 2025. A survey of table reasoning with large language models. Frontiers of Computer Science, 19(9):199348. find
  42. Yunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon, Shaleen Deep, and Jignesh M Patel. 2023. Reactable: Enhancing react for table question answering. arXiv preprint arXiv:2310.00815. — [arXiv:2310.00815](https://arxiv.org/abs/2310.00815) find
  43. Yilun Zhao, Lyuhao Chen, Arman Cohan, and Chen Zhao. 2024. Tapera: enhancing faithfulness and interpretability in long-form table qa by content planning and execution-based reasoning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… find
  44. Wei Zhou, Mohsen Mesgar, Annemarie Friedrich, and Heike Adel. 2025a. Efficient multi-agent collaboration with tool use for online planning in complex table question answering. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 945–968. find
  45. Yixiao Zhou, Yang Li, Dongzhou Cheng, Hehe Fan, and Yu Cheng. 2026. Look inward to explore outward: Learning temperature policy from llm internal states via hierarchical rl. arXiv preprint arXiv:2602.13035. — [arXiv:2602.13035](https://arxiv.org/abs/2602.13035) find
  46. Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, Zhiliang Wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, and Hehe Fan. 2025b. Dropping experts, recombining neurons: Retraining-free pruning for sparse mixture-of-experts llms. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15169– 1518… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ye-2026-when-tableqa-meets-noise-dual/