---
title: "CompTab — paper by Yang et al. (2026) — summary and ideas"
description: "Most TableQA benchmarks use tidy, well-formed tables, so they overstate how well LLMs handle the messy tables found in… 57 references."
authors: ["Zhen Yang", "Wei Du", "Jie Wang", "Wenze Zhou", "Xiangfeng Meng", "Zhengyang Wang", "Suping Sun", "Ziwei Du", "Haodong Zou", "Jie Chen", "Yongbin Liu", "Shicheng Tan", "Jiahao Ying", "Shu Zhao"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1279/"
doi: "10.18653/v1/2026.acl-long.1279"
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/yang-2026-comptab-comprehensive-benchmark-real-world/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-comptab-comprehensive-benchmark-real-world/)

[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/27/) / CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables

# CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables

**Authors:** [Zhen Yang](https://md.research.elamur.ai/free/en/authors/zhen-yang/), [Wei Du](https://md.research.elamur.ai/free/en/authors/wei-du/), [Jie Wang](https://md.research.elamur.ai/free/en/authors/jie-wang/), Wenze Zhou, Xiangfeng Meng, [Zhengyang Wang](https://md.research.elamur.ai/free/en/authors/zhengyang-wang/), Suping Sun, Ziwei Du, [Haodong Zou](https://md.research.elamur.ai/free/en/authors/haodong-zou/), [Jie Chen](https://md.research.elamur.ai/free/en/authors/jie-chen/), [Yongbin Liu](https://md.research.elamur.ai/free/en/authors/yongbin-liu/), [Shicheng Tan](https://md.research.elamur.ai/free/en/authors/shicheng-tan/), [Jiahao Ying](https://md.research.elamur.ai/free/en/authors/jiahao-ying/) and [Shu Zhao](https://md.research.elamur.ai/free/en/authors/shu-zhao/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1279/) · [PDF](https://aclanthology.org/2026.acl-long.1279.pdf) · [DOI 10.18653/v1/2026.acl-long.1279](https://doi.org/10.18653/v1/2026.acl-long.1279) · [OpenAlex](https://openalex.org/W7166840439)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Most TableQA benchmarks use tidy, well-formed tables, so they overstate how well LLMs handle the messy tables found in practice. CompTab addresses this by combining six difficulty types in one benchmark: semantic ambiguity, multi-hop reasoning, transposed layouts, merged cells, missing values and outliers. The authors start from anonymized seed table–question pairs drawn from 12 domains. They expand these with category-specific prompting of Claude-sonnet-4 and then manually check samples for structural validity, answerability and type fidelity. They also build CompTabInstruct, which mixes textual Direct Prompting (DP) reasoning with executable Python Agent (PyAgent) traces. A two-step recipe uses this data to produce CompTabLLM: SFT on DP trajectories, followed by DPO on PyAgent-level decisions. Across 38 open- and closed-source LLMs, performance drops sharply under realistic conditions, while the proposed training gives consistent gains. The result is a unified testbed for robust, real-world table reasoning.

## Key points
- GPT-4o scores about 83% on WTQ and 93% on TabFact but only about 34% on CompTab's irregular and complex tables.
- Each sample receives one dominant category, although types may overlap. A question counts as multi-hop when it needs more than three interdependent operations.
- In the generation pipeline, each round produces one table with three questions. A random 10% of the output is inspected by hand, and faulty instances are dropped.
- Training-dynamics experiments at 3k, 6k and 10k data scales show that larger sets give smoother SFT curves and stronger DPO reward margins.
- DP does better on sum and "how many" questions, which need global aggregation. PyAgent wins on conditional and "what" questions, which reduce to filtering or record selection.

*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

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 415 works · 94,028 citations
- [Singapore Management University](https://md.research.elamur.ai/free/en/universities/singapore-management-university/) — University, Singapore, Singapore · 35 works · 2,457 citations
- [Anhui University](https://md.research.elamur.ai/free/en/universities/anhui-university/) — University, Hefei, China · 11 works · 7 citations
- [University of South China](https://md.research.elamur.ai/free/en/universities/university-of-south-china/) — University, Hengyang, China · 2 works

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works

## Cite

Cite as: Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying and Shu Zhao. 2026. CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular 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.

```bibtex
@inproceedings{yang2026comptab,
  title = {{CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables}},
  author = {Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying and Shu Zhao},
  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.1279},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1279}
}
```

- [← previous Compression-based Language Complexity under Register Variation in Portuguese](https://md.research.elamur.ai/free/en/papers/serras-2026-compression-based-language-complexity-under/)
- [next → Computational Benchmarks for Egyptian Arabic Child Directed Speech](https://md.research.elamur.ai/free/en/papers/khalifa-2026-computational-benchmarks-egyptian-arabic-child/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/)

## References

57 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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.
2. Mohammad S Ahmad, Zan A Naeem, MichaÃG , l Aupetit, Ahmed Elmagarmid, Mohamed Eltabakh, Xi-asong Ma, Mourad Ouzzani, and Chaoyi Ruan. 2025. Hct-qa: A benchmark for question answering on human-centric tables. arXiv preprint arXiv:2504.20047. — [arXiv:2504.20047](https://arxiv.org/abs/2504.20047) [find](https://scholar.google.com/scholar?q=Mohammad+S+Ahmad%2C+Zan+A+Naeem%2C+Micha%C3%83G+%2C+l+Aupetit%2C+Ahmed+Elmagarmid%2C+Mohamed+Eltabakh%2C+Xi%2Dasong+Ma%2C+Mourad+Ouzzani%2C+and+Chaoyi+Ruan%2E+2025%2E+Hct%2Dqa%3A+A+benchmark+for+question+answering+on+human%2Dcentric+)
3. Chahrazed B. Bachir Belmehdi, Abderrahmane Khiat, and Nabil Keskes. 2024. Predicting an optimal virtual data model for uniform access to large heterogeneous data. DATA INTELLIGENCE, 6(2):504–530. [find](https://scholar.google.com/scholar?q=Chahrazed+B%2E+Bachir+Belmehdi%2C+Abderrahmane+Khiat%2C+and+Nabil+Keskes%2E+2024%2E+Predicting+an+optimal+virtual+data+model+for+uniform+access+to+large+heterogeneous+data%2E+DATA+INTELLIGENCE%2C+6%282%29%3A504%E2%80%93530%2E)
4. Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, and 1 others. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954. [find](https://scholar.google.com/scholar?q=Xiao+Bi%2C+Deli+Chen%2C+Guanting+Chen%2C+Shanhuang+Chen%2C+Damai+Dai%2C+Chengqi+Deng%2C+Honghui+Ding%2C+Kai+Dong%2C+Qiushi+Du%2C+Zhe+Fu%2C+and+1+others%2E+2024%2E+Deepseek+llm%3A+Scaling+open%2Dsource+language+models+with+longte)
5. F Bressand, G Lengyel, G Lample, L Saulnier, and 1 others. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [find](https://scholar.google.com/scholar?q=F+Bressand%2C+G+Lengyel%2C+G+Lample%2C+L+Saulnier%2C+and+1+others%2E+2023%2E+Mistral+7b%2E+arXiv+preprint+arXiv%3A2310%2E06825%2E)
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in Neural Information Processing Systems, 33:1877–1901.
7. Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, and 1 others. 2025. [Minimax-m1: Scaling test-time compute efficiently with lightning attention](https://md.research.elamur.ai/free/en/papers/minimax-2025-minimax-m1-scaling-test/). arXiv preprint arXiv:2506.13585.
8. Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, and William Yang Wang. 2019. [Tabfact: A large-scale dataset for table-based fact verification](https://md.research.elamur.ai/free/en/papers/chen-2019-tabfact-large-scale-dataset-table/). In International Conference on Learning Representations.
9. Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan R Routledge, and 1 others. 2021. [Finqa: A dataset of numerical reasoning over financial data](https://md.research.elamur.ai/free/en/papers/chen-2021-finqa-dataset-numerical-reasoning-over/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Langua…
10. Naihao Deng, Zhenjie Sun, Ruiqi He, Aman Sikka, Yulong Chen, Lin Ma, Yue Zhang, and Rada Mihalcea. 2024. Tables as texts or images: Evaluating the table reasoning ability of llms and mllms. In Findings of the Association for Computational Linguistics ACL, pages 407–426. [find](https://scholar.google.com/scholar?q=Naihao+Deng%2C+Zhenjie+Sun%2C+Ruiqi+He%2C+Aman+Sikka%2C+Yulong+Chen%2C+Lin+Ma%2C+Yue+Zhang%2C+and+Rada+Mihalcea%2E+2024%2E+Tables+as+texts+or+images%3A+Evaluating+the+table+reasoning+ability+of+llms+and+mllms%2E+In+Finding)
11. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
12. Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, and Noah D Goodman. 2025. [Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars](https://md.research.elamur.ai/free/en/papers/gandhi-2025-cognitive-behaviors-that-enable-self/). arXiv preprint arXiv:2503.01307.
13. Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, and 1 others. 2024. [Chatglm: A family of large language models from glm-130b to glm-4 all tools](https://md.research.elamur.ai/free/en/papers/glm-2024-chatglm-family-large-language-models/). arXiv preprint arXiv:2406.12793.
14. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Yu Wu, YK Li, and 1 others. 2024. Deepseek-coder: When the large language model meets programming–the rise of code intelligence. arXiv preprint arXiv:2401.14196. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Qihao+Zhu%2C+Dejian+Yang%2C+Zhenda+Xie%2C+Kai+Dong%2C+Wentao+Zhang%2C+Guanting+Chen%2C+Xiao+Bi%2C+Yu+Wu%2C+YK+Li%2C+and+1+others%2E+2024%2E+Deepseek%2Dcoder%3A+When+the+large+language+model+meets+programming%E2%80%93the+rise)
15. Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, and Zhenyu Chen. 2025. [Token-budget-aware llm reasoning](https://md.research.elamur.ai/free/en/papers/han-2024-token-budget-aware-llm-reasoning/). In Findings of the Association for Computational Linguistics: ACL, pages 24842–24855.
16. Xinyi He, Mengyu Zhou, Xinrun Xu, Xiaojun Ma, Rui Ding, Lun Du, Yan Gao, Ran Jia, Xu Chen, Shi Han, and 1 others. 2024. Text2analysis: A benchmark of table question answering with advanced data analysis and unclear queries. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38,… [find](https://scholar.google.com/scholar?q=Xinyi+He%2C+Mengyu+Zhou%2C+Xinrun+Xu%2C+Xiaojun+Ma%2C+Rui+Ding%2C+Lun+Du%2C+Yan+Gao%2C+Ran+Jia%2C+Xu+Chen%2C+Shi+Han%2C+and+1+others%2E+2024%2E+Text2analysis%3A+A+benchmark+of+table+question+answering+with+advanced+data+analys)
17. Zixian Huang, Wenhao Zhu, Gong Cheng, Lei Li, and Fei Yuan. 2024. Mindmerger: Efficiently boosting llm reasoning in non-english languages. Advances in Neural Information Processing Systems, 37:34161– 34187. [find](https://scholar.google.com/scholar?q=Zixian+Huang%2C+Wenhao+Zhu%2C+Gong+Cheng%2C+Lei+Li%2C+and+Fei+Yuan%2E+2024%2E+Mindmerger%3A+Efficiently+boosting+llm+reasoning+in+non%2Denglish+languages%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A34161%E2%80%93+)
18. Mohit Iyyer, Wen-tau Yih, and Ming-Wei Chang. 2017. [Search-based neural structured learning for sequential question answering](https://md.research.elamur.ai/free/en/papers/iyyer-2017-search-based-neural-structured-learning/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1821– 1831.
19. Xingyu Ji, Aditya Parameswaran, and Madelon Hulsebos. Target: Benchmarking table retrieval for generative tasks. In NeurIPS 2024 Third Table Representation Learning Workshop. [find](https://scholar.google.com/scholar?q=Xingyu+Ji%2C+Aditya+Parameswaran%2C+and+Madelon+Hulsebos%2E+Target%3A+Benchmarking+table+retrieval+for+generative+tasks%2E+In+NeurIPS+2024+Third+Table+Representation+Learning+Workshop%2E)
20. Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, and 1 others. 2022. Ait-qa: Question answering dataset over complex tables in the airline industry. In Proceedings of the North Amer… [find](https://scholar.google.com/scholar?q=Yannis+Katsis%2C+Saneem+Chemmengath%2C+Vishwajeet+Kumar%2C+Samarth+Bharadwaj%2C+Mustafa+Canim%2C+Michael+Glass%2C+Alfio+Gliozzo%2C+Feifei+Pan%2C+Jaydeep+Sen%2C+Karthik+Sankaranarayanan%2C+and+1+others%2E+2022%2E+Ait%2Dqa%3A+Ques)
21. Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, and 1 others. 2023. [Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls](https://md.research.elamur.ai/free/en/papers/li-2023-llm-already-serve-database-interface/). Advances in Neural Information Processing Systems, 36:42330–4…
22. Zheng Li, Yang Du, Mao Zheng, and Mingyang Song. 2025. Mimotable: A multi-scale spreadsheet benchmark with meta operations for table reasoning. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2548–2560. [find](https://scholar.google.com/scholar?q=Zheng+Li%2C+Yang+Du%2C+Mao+Zheng%2C+and+Mingyang+Song%2E+2025%2E+Mimotable%3A+A+multi%2Dscale+spreadsheet+benchmark+with+meta+operations+for+table+reasoning%2E+In+Proceedings+of+the+31st+International+Conference+on+C)
23. Tianyang Liu, Fei Wang, and Muhao Chen. 2024. Rethinking tabular data understanding with large language models. In Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 450–482. [find](https://scholar.google.com/scholar?q=Tianyang+Liu%2C+Fei+Wang%2C+and+Muhao+Chen%2E+2024%2E+Rethinking+tabular+data+understanding+with+large+language+models%2E+In+Proceedings+of+the+North+American+Chapter+of+the+Association+for+Computational+Lingui)
24. Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Hailey Schoelkopf, Riley Kong, Xiangru Tang, and 1 others. 2022. [Fetaqa: Free-form table question answering](https://md.research.elamur.ai/free/en/papers/nan-2022-fetaqa-free-form-table-question/). Transactions of the Association for Computational Linguistics, 10:35–49.
25. Panupong Pasupat and Percy Liang. 2015. [Compositional semantic parsing on semi-structured tables](https://md.research.elamur.ai/free/en/papers/pasupat-2015-compositional-semantic-parsing-semi-structured/). 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–…
26. Sohan Patnaik, Heril Changwal, Milan Aggarwal, Sumit Bhatia, Yaman Kumar, and Balaji Krishnamurthy. 2024. Cabinet: Content relevance-based noise reduction for table question answering. In The 12th International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Sohan+Patnaik%2C+Heril+Changwal%2C+Milan+Aggarwal%2C+Sumit+Bhatia%2C+Yaman+Kumar%2C+and+Balaji+Krishnamurthy%2E+2024%2E+Cabinet%3A+Content+relevance%2Dbased+noise+reduction+for+table+question+answering%2E+In+The+12th+Int)
27. Shraman Pramanick, Rama Chellappa, and Subhashini Venugopalan. 2024. Spiqa: A dataset for multimodal question answering on scientific papers. Advances in Neural Information Processing Systems, 37:118807– 118833. [find](https://scholar.google.com/scholar?q=Shraman+Pramanick%2C+Rama+Chellappa%2C+and+Subhashini+Venugopalan%2E+2024%2E+Spiqa%3A+A+dataset+for+multimodal+question+answering+on+scientific+papers%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A1188)
28. Zipeng Qiu, You Peng, Guangxin He, Binhang Yuan, and Chen Wang. 2024. Tqa-bench: Evaluating llms for multi-table question answering with scalable context and symbolic extension. arXiv preprint arXiv:2411.19504. — [arXiv:2411.19504](https://arxiv.org/abs/2411.19504) [find](https://scholar.google.com/scholar?q=Zipeng+Qiu%2C+You+Peng%2C+Guangxin+He%2C+Binhang+Yuan%2C+and+Chen+Wang%2E+2024%2E+Tqa%2Dbench%3A+Evaluating+llms+for+multi%2Dtable+question+answering+with+scalable+context+and+symbolic+extension%2E+arXiv+preprint+arXiv%3A2)
29. Xiangru Tang, Yiming Zong, Jason Phang, Yilun Zhao, Wangchunshu Zhou, Arman Cohan, and Mark Gerstein. 2024. Struc-bench: Are large language models good at generating complex structured tabular data? In Proceedings of the Conference of the North American Chapter of the Association for Computational L… [find](https://scholar.google.com/scholar?q=Xiangru+Tang%2C+Yiming+Zong%2C+Jason+Phang%2C+Yilun+Zhao%2C+Wangchunshu+Zhou%2C+Arman+Cohan%2C+and+Mark+Gerstein%2E+2024%2E+Struc%2Dbench%3A+Are+large+language+models+good+at+generating+complex+structured+tabular+data%3F+I)
30. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805.
31. Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, and 1 others. 2025. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). arXiv preprint arXiv:2507.20534.
32. Qwen Team and 1 others. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671, 2(3). [find](https://scholar.google.com/scholar?q=Qwen+Team+and+1+others%2E+2024%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2C+2%283%29%2E)
33. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, and 1 others. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
34. Dong Wang, Xiyue Wang, Haoqi Zheng, and 1 others. 2025a. Tablecritic: Refine table reasoning via self-criticism and tool library. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 47. [find](https://scholar.google.com/scholar?q=Dong+Wang%2C+Xiyue+Wang%2C+Haoqi+Zheng%2C+and+1+others%2E+2025a%2E+Tablecritic%3A+Refine+table+reasoning+via+self%2Dcriticism+and+tool+library%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Cognitive+Science+Society%2C)
35. Jing Wang, Shuo Zhang, and Runzhi Li. 2024a. Gate feature interaction network for relation prediction in knowledge graph. DATA INTELLIGENCE, 6(3):749– 770. [find](https://scholar.google.com/scholar?q=Jing+Wang%2C+Shuo+Zhang%2C+and+Runzhi+Li%2E+2024a%2E+Gate+feature+interaction+network+for+relation+prediction+in+knowledge+graph%2E+DATA+INTELLIGENCE%2C+6%283%29%3A749%E2%80%93+770%2E)
36. Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, and Yangqiu Song. 2024b. [Rethinking the bounds of llm reasoning: Are multi-agent discussions the key?](https://md.research.elamur.ai/free/en/papers/wang-2024-rethinking-bounds-llm-reasoning/) In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6106–6131.
37. Yuxiang Wang, Junhao Gan, and Jianzhong Qi. 2025b. 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](https://scholar.google.com/scholar?q=Yuxiang+Wang%2C+Junhao+Gan%2C+and+Jianzhong+Qi%2E+2025b%2E+Tabsd%3A+Large+free%2Dform+table+question+answering+with+sql%2Dbased+table+decomposition%2E+arXiv+preprint+arXiv%3A2502%2E13422%2E+%E2%80%94+%5BarXiv%3A2502%2E13422%5D%28https%3A%2F%2Farx)
38. Sujoy Roychowdhury, Sumit Soman, HG Ranjani, Avantika Sharma, Neeraj Gunda, and Sai Krishna Bala. 2024. Evaluation of table representations to answer questions from tables in documents: A case study using 3gpp specifications. arXiv preprint arXiv:2408.17008. — [arXiv:2408.17008](https://arxiv.org/abs/2408.17008) [find](https://scholar.google.com/scholar?q=Sujoy+Roychowdhury%2C+Sumit+Soman%2C+HG+Ranjani%2C+Avantika+Sharma%2C+Neeraj+Gunda%2C+and+Sai+Krishna+Bala%2E+2024%2E+Evaluation+of+table+representations+to+answer+questions+from+tables+in+documents%3A+A+case+study+u)
39. Zhensheng Wang, Wenmian Yang, Kun Zhou, Yiquan Zhang, and Weijia Jia. 2025c. Retqa: A large-scale open-domain tabular question answering dataset for real estate sector. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25452–25460. [find](https://scholar.google.com/scholar?q=Zhensheng+Wang%2C+Wenmian+Yang%2C+Kun+Zhou%2C+Yiquan+Zhang%2C+and+Weijia+Jia%2E+2025c%2E+Retqa%3A+A+large%2Dscale+open%2Ddomain+tabular+question+answering+dataset+for+real+estate+sector%2E+In+Proceedings+of+the+AAAI+Conf)
40. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, and 1 others. 2023. [Code llama: Open foundation models for code](https://md.research.elamur.ai/free/en/papers/roziere-2024-code-llama-open-foundation-models/). arXiv preprint arXiv:2308.12950.
41. Jian Wu, Linyi Yang, Dongyuan Li, Yuliang Ji, Manabu Okumura, and Yue Zhang. 2025a. Mmqa: Evaluating llms with multi-table multi-hop complex questions. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jian+Wu%2C+Linyi+Yang%2C+Dongyuan+Li%2C+Yuliang+Ji%2C+Manabu+Okumura%2C+and+Yue+Zhang%2E+2025a%2E+Mmqa%3A+Evaluating+llms+with+multi%2Dtable+multi%2Dhop+complex+questions%2E+In+The+Thirteenth+International+Conference+on+Le)
42. Junde Wu, Jiayuan Zhu, Yuyuan Liu, Min Xu, and Yueming Jin. 2025b. [Agentic reasoning: A streamlined framework for enhancing llm reasoning with agentic tools](https://md.research.elamur.ai/free/en/papers/wu-2025-agentic-reasoning-streamlined-framework-enhancing/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 28489– 28503.
43. Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, and 1 others. 2025c. Realhitbench: A comprehensive realistic hierarchical table benchmark for evaluating llm-based table analysis. arXiv preprint arXiv:2506.13405. [find](https://scholar.google.com/scholar?q=Pengzuo+Wu%2C+Yuhang+Yang%2C+Guangcheng+Zhu%2C+Chao+Ye%2C+Hong+Gu%2C+Xu+Lu%2C+Ruixuan+Xiao%2C+Bowen+Bao%2C+Yijing+He%2C+Liangyu+Zha%2C+and+1+others%2E+2025c%2E+Realhitbench%3A+A+comprehensive+realistic+hierarchical+table+bench)
44. Xianjie Wu, Jian Yang, Linzheng Chai, Ge Zhang, Jiaheng Liu, Xeron Du, Di Liang, Daixin Shu, Xianfu Cheng, Tianzhen Sun, and 1 others. 2025d. Tablebench: A comprehensive and complex benchmark for table question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, p… [find](https://scholar.google.com/scholar?q=Xianjie+Wu%2C+Jian+Yang%2C+Linzheng+Chai%2C+Ge+Zhang%2C+Jiaheng+Liu%2C+Xeron+Du%2C+Di+Liang%2C+Daixin+Shu%2C+Xianfu+Cheng%2C+Tianzhen+Sun%2C+and+1+others%2E+2025d%2E+Tablebench%3A+A+comprehensive+and+complex+benchmark+for+tabl)
45. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. 2023. [Wizardlm: Empowering large language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). arXiv preprint arXiv:2304.12244. task. In Proceedings of the Conference on Empirical Methods in Natural Language Proces…
46. Jinghan Zhang, Xiting Wang, Weijieying Ren, Lu Jiang, Dongjie Wang, and Kunpeng Liu. 2025b. Ratt: A thought structure for coherent and correct llm reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 26733–26741. [find](https://scholar.google.com/scholar?q=Jinghan+Zhang%2C+Xiting+Wang%2C+Weijieying+Ren%2C+Lu+Jiang%2C+Dongjie+Wang%2C+and+Kunpeng+Liu%2E+2025b%2E+Ratt%3A+A+thought+structure+for+coherent+and+correct+llm+reasoning%2E+In+Proceedings+of+the+AAAI+Conference+on+A)
47. Siyue Zhang, Luu Anh Tuan, and Chen Zhao. 2024. Syntqa: Synergistic table-based question answering via mixture of text-to-sql and e2e tqa. In Findings of the Association for Computational Linguistics: EMNLP, pages 2352–2364. [find](https://scholar.google.com/scholar?q=Siyue+Zhang%2C+Luu+Anh+Tuan%2C+and+Chen+Zhao%2E+2024%2E+Syntqa%3A+Synergistic+table%2Dbased+question+answering+via+mixture+of+text%2Dto%2Dsql+and+e2e+tqa%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
48. Zhehao Zhang, Xitao Li, Yan Gao, and Jian-Guang Lou. 2023. Crt-qa: A dataset of complex reasoning question answering over tabular data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2131–2153. [find](https://scholar.google.com/scholar?q=Zhehao+Zhang%2C+Xitao+Li%2C+Yan+Gao%2C+and+Jian%2DGuang+Lou%2E+2023%2E+Crt%2Dqa%3A+A+dataset+of+complex+reasoning+question+answering+over+tabular+data%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Na)
49. Victor Zhong, Caiming Xiong, and Richard Socher. 2017. [Seq2sql: Generating structured queries from natural language using reinforcement learning](https://md.research.elamur.ai/free/en/papers/zhong-2017-seq2sql-generating-structured-queries-natural/). arXiv preprint arXiv:1709.00103.
50. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
51. Wei Zhou, Mohsen Mesgar, Heike Adel, and Annemarie Friedrich. 2024. Freb-tqa: A fine-grained robustness evaluation benchmark for table question answering. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol… [find](https://scholar.google.com/scholar?q=Wei+Zhou%2C+Mohsen+Mesgar%2C+Heike+Adel%2C+and+Annemarie+Friedrich%2E+2024%2E+Freb%2Dtqa%3A+A+fine%2Dgrained+robustness+evaluation+benchmark+for+table+question+answering%2E+In+Proceedings+of+the+Conference+of+the+North)
52. Zhen Yang, Ziwei Du, Minghan Zhang, Wei Du, Jie Chen, Zhen Duan, and Shu Zhao. 2025b. Triples as the key: Structuring makes decomposition and verification easier in llm-based tableqa. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zhen+Yang%2C+Ziwei+Du%2C+Minghan+Zhang%2C+Wei+Du%2C+Jie+Chen%2C+Zhen+Duan%2C+and+Shu+Zhao%2E+2025b%2E+Triples+as+the+key%3A+Structuring+makes+decomposition+and+verification+easier+in+llm%2Dbased+tableqa%2E+In+The+Thirteent)
53. Alex Zhuang, Ge Zhang, Tianyu Zheng, Xinrun Du, Junjie Wang, Weiming Ren, Stephen W Huang, Jie Fu, Xiang Yue, and Wenhu Chen. 2024. Structlm: Towards building generalist models for structured knowledge grounding. arXiv preprint arXiv:2402.16671. — [arXiv:2402.16671](https://arxiv.org/abs/2402.16671) [find](https://scholar.google.com/scholar?q=Alex+Zhuang%2C+Ge+Zhang%2C+Tianyu+Zheng%2C+Xinrun+Du%2C+Junjie+Wang%2C+Weiming+Ren%2C+Stephen+W+Huang%2C+Jie+Fu%2C+Xiang+Yue%2C+and+Wenhu+Chen%2E+2024%2E+Structlm%3A+Towards+building+generalist+models+for+structured+knowledg)
54. Zhen Yang, Ziwei Du, Minghan Zhang, Wei Du, Jie Chen, Fulan Qian, and Shu Zhao. 2025c. Causality meets the table: Debiasing llms for faithful tableqa via front-door intervention. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Zhen+Yang%2C+Ziwei+Du%2C+Minghan+Zhang%2C+Wei+Du%2C+Jie+Chen%2C+Fulan+Qian%2C+and+Shu+Zhao%2E+2025c%2E+Causality+meets+the+table%3A+Debiasing+llms+for+faithful+tableqa+via+front%2Ddoor+intervention%2E+In+Advances+in+Neural)
55. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, and 1 others. 2018. [Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task](https://md.research.elamur.ai/free/en/papers/yu-2018-spider-large-scale-human-labeled/). In Proceedings of the Conference on Empirical…
56. Daojian Zeng, Lin Zhou, Zhiheng Zhang, and Lincheng Jiang. 2025. Autogen: Automated tool learning data generation with domain-specific structured data. DATA INTELLIGENCE, 7(4):1108–1128. [find](https://scholar.google.com/scholar?q=Daojian+Zeng%2C+Lin+Zhou%2C+Zhiheng+Zhang%2C+and+Lincheng+Jiang%2E+2025%2E+Autogen%3A+Automated+tool+learning+data+generation+with+domain%2Dspecific+structured+data%2E+DATA+INTELLIGENCE%2C+7%284%29%3A1108%E2%80%931128%2E)
57. Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, and 1 others. 2025a. T2r-bench: A benchmark for real world table-to-report [find](https://scholar.google.com/scholar?q=Jie+Zhang%2C+Changzai+Pan%2C+Sishi+Xiong%2C+Kaiwen+Wei%2C+Yu+Zhao%2C+Xiangyu+Li%2C+Jiaxin+Peng%2C+Xiaoyan+Gu%2C+Jian+Yang%2C+Wenhan+Chang%2C+and+1+others%2E+2025a%2E+T2r%2Dbench%3A+A+benchmark+for+real+world+table%2Dto%2Dreport)

*Updated 2 November 2026*