---
title: "TabularMath — paper by Tian et al. (2026) — summary and ideas"
description: "The authors introduce AutoT2T, a neuro-symbolic pipeline that converts GSM8K-style word problems… 53 references, cited by 3 papers here."
authors: ["Shi-Yu Tian", "Zhi Zhou", "Wei Dong", "Kun-Yang Yu", "Ming Yang", "Zi-Jian Cheng", "Lan-Zhe Guo", "Yu-Feng Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.759/"
doi: "10.18653/v1/2026.findings-acl.759"
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/tian-2026-tabularmath-understanding-math-reasoning-over/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tian-2026-tabularmath-understanding-math-reasoning-over/)

[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/6/) / TabularMath: Understanding Math Reasoning over Tables with Large Language Models

# TabularMath: Understanding Math Reasoning over Tables with Large Language Models

**Authors:** Shi-Yu Tian, Zhi Zhou, [Wei Dong](https://md.research.elamur.ai/free/en/authors/wei-dong/), Kun-Yang Yu, [Ming Yang](https://md.research.elamur.ai/free/en/authors/ming-yang/), Zi-Jian Cheng, [Lan-Zhe Guo](https://md.research.elamur.ai/free/en/authors/lan-zhe-guo/) and Yu-Feng 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.759/) · [PDF](https://aclanthology.org/2026.findings-acl.759.pdf) · [DOI 10.18653/v1/2026.findings-acl.759](https://doi.org/10.18653/v1/2026.findings-acl.759) · [OpenAlex](https://openalex.org/W4414586680)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/tian-2026-tabularmath-understanding-math-reasoning-over/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most math benchmarks for LLMs use plain-text word problems. Real tasks such as business intelligence or financial reports instead require multi-step arithmetic over tables that may be large, incomplete, or contradictory. Existing table benchmarks rely on manual collection, which limits their scale, and they seldom test whether a model notices flawed data. The authors introduce AutoT2T, a neuro-symbolic pipeline that converts GSM8K-style word problems into tabular tasks without human annotation. An LLM first formalizes each problem as variables and constraints, and an SMT solver (Z3 or CVC5) checks that formulation. The verified components are then rewritten into a seed table, which is expanded through randomized augmentation. Using this pipeline they build TabularMath, with Easy, Medium, Hard and Imperfect subsets, each in text and image form. Across 18 models, accuracy falls as tables become more complex, and most models fail to flag missing or conflicting data. Text tables are easier than images, even for multimodal models. The pipeline also yields useful training data, giving a scalable way to test both accuracy and robustness.

## Key points
- **Pipeline and dataset size:** AutoT2T has three stages: semantic decoupling (SMT-Lib-style modeling), table transformation, and augmentation. The augmentation step uses four strategies: RowAug, ColAug, OrdShf and InfMut. TabularMath contains 3,391 unique tables; rendering each one with matplotlib gives 6,782 samples in total.
- **Retrieval versus reasoning:** Retrieving values alone is much easier than retrieving and reasoning together, with a gap above 20% on average. On the Imperfect subset, some models give misleading answers more than 50% of the time.
- **Effect of warning models:** When models are told that inputs may be flawed, they score lower on well-posed problems. This shows a trade-off between solving problems and detecting faulty ones.
- **Table format:** Text tables beat image tables by 0.89–3.07 percentage points, even for MLLMs. Among text formats, JSON and serialized key-value layouts outperform Markdown, and the gap grows as tables get harder.
- **Fine-tuning:** About 6K AutoT2T samples derived from GSM8K were used to fine-tune Qwen2.5-3B and Qwen2.5-7B. This raised TabularMath scores by roughly 15% on average and improved TAT-QA, FinQA and TabMWP by about 4%.

*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

- [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 74 works · 7,814 citations

📚 Shelves (6): [🖥️ 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 · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 252 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Shi-Yu Tian, Zhi Zhou, Wei Dong, Kun-Yang Yu, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo and Yu-Feng Li. 2026. TabularMath: Understanding Math Reasoning over Tables with Large Language Models. 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{tian2026tabularmath,
  title = {{TabularMath: Understanding Math Reasoning over Tables with Large Language Models}},
  author = {Shi-Yu Tian, Zhi Zhou, Wei Dong, Kun-Yang Yu, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo and Yu-Feng Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.759},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.759}
}
```

- [← previous SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis](https://md.research.elamur.ai/free/en/papers/wu-2026-synthrl-scaling-visual-reasoning-verifiable/)
- [next → Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts](https://md.research.elamur.ai/free/en/papers/qing-2026-tailoring-memory-granularity-multi-hop/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

53 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Haniel Barbosa, Clark Barrett, Martin Brain, Gereon Kremer, Hanna Lachnitt, Makai Mann, Abdalrhman Mohamed, Mudathir Mohamed, Aina Niemetz, Andres Nötzli, and 1 others. 2022. cvc5: A versatile Clark Barrett, Aaron Stump, Cesare Tinelli, and 1 others. 2010. The smt-lib standard: Version 2.0. In Proce… [find](https://scholar.google.com/scholar?q=Haniel+Barbosa%2C+Clark+Barrett%2C+Martin+Brain%2C+Gereon+Kremer%2C+Hanna+Lachnitt%2C+Makai+Mann%2C+Abdalrhman+Mohamed%2C+Mudathir+Mohamed%2C+Aina+Niemetz%2C+Andres+N%C3%B6tzli%2C+and+1+others%2E+2022%2E+cvc5%3A+A+versatile+Clark+B)
2. Ethan Bradley, Muhammad Roman, Karen Rafferty, and Barry Devereux. 2024. Synfintabs: a dataset of synthetic financial tables for information and table extraction. arXiv preprint arXiv:2412.04262. — [arXiv:2412.04262](https://arxiv.org/abs/2412.04262) [find](https://scholar.google.com/scholar?q=Ethan+Bradley%2C+Muhammad+Roman%2C+Karen+Rafferty%2C+and+Barry+Devereux%2E+2024%2E+Synfintabs%3A+a+dataset+of+synthetic+financial+tables+for+information+and+table+extraction%2E+arXiv+preprint+arXiv%3A2412%2E04262%2E+%E2%80%94+%5Ba)
3. Paola Cerchiello and Paolo Giudici. 2016. Big data analysis for financial risk management. Journal of Big Data, 3(1):18. [find](https://scholar.google.com/scholar?q=Paola+Cerchiello+and+Paolo+Giudici%2E+2016%2E+Big+data+analysis+for+financial+risk+management%2E+Journal+of+Big+Data%2C+3%281%29%3A18%2E)
4. Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Wang, and William W Cohen. 2020. Open question answering over tables and text. arXiv preprint arXiv:2010.10439. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Ming%2DWei+Chang%2C+Eva+Schlinger%2C+William+Wang%2C+and+William+W+Cohen%2E+2020%2E+Open+question+answering+over+tables+and+text%2E+arXiv+preprint+arXiv%3A2010%2E10439%2E)
5. 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/). arXiv preprint arXiv:1909.02164.
6. Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan 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/). arXiv preprint arXiv:2109.00122.
7. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
8. Runpeng Dai, Run Yang, Fan Zhou, and Hongtu Zhu. 2026. Breach in the shield: Unveiling the vulnerabilities of large language models. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3509–3521. [find](https://scholar.google.com/scholar?q=Runpeng+Dai%2C+Run+Yang%2C+Fan+Zhou%2C+and+Hongtu+Zhu%2E+2026%2E+Breach+in+the+shield%3A+Unveiling+the+vulnerabilities+of+large+language+models%2E+In+Proceedings+of+the+19th+Conference+of+the+European+Chapter+of+th)
9. Leonardo Mendonça de Moura and Nikolaj S. Bjørner. 2008. Z3: an efficient SMT solver. In Procddings of the 14th Tools and Algorithms for the Construction and Analysis of Systems International Conference, volume 4963 of Lecture Notes in Computer Science, pages 337–340. [find](https://scholar.google.com/scholar?q=Leonardo+Mendon%C3%A7a+de+Moura+and+Nikolaj+S%2E+Bj%C3%B8rner%2E+2008%2E+Z3%3A+an+efficient+SMT+solver%2E+In+Procddings+of+the+14th+Tools+and+Algorithms+for+the+Construction+and+Analysis+of+Systems+International+Conferen)
10. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Pal: Program-aided language models. In Proceedings of the 40th International Conference on Machine Learning, pages 10764– 10799. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+Uri+Alon%2C+Pengfei+Liu%2C+Yiming+Yang%2C+Jamie+Callan%2C+and+Graham+Neubig%2E+2023%2E+Pal%3A+Program%2Daided+language+models%2E+In+Proceedings+of+the+40th+International+Conference+o)
11. Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, Hao Yu, Hongning Wang, Jiadai Sun, Jiajie Zhang, Jiale Cheng, Jiayi Gui, Jie Tang, Jing Zhang, Juanzi Li, and 37 others. 2024. [Chatglm: A family of large language models from glm-130b t…](https://md.research.elamur.ai/free/en/papers/glm-2024-chatglm-family-large-language-models/)
12. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, 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 preprint arXiv:2407.21783.
13. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025a. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
14. Ruiling Guo, Xinwei Yang, Chen Huang, Tong Zhang, and Yong Hu. 2025b. Candy: Benchmarking llms limitations and assistive potential in chinese misinformation fact-checking. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5724–5758. [find](https://scholar.google.com/scholar?q=Ruiling+Guo%2C+Xinwei+Yang%2C+Chen+Huang%2C+Tong+Zhang%2C+and+Yong+Hu%2E+2025b%2E+Candy%3A+Benchmarking+llms+limitations+and+assistive+potential+in+chinese+misinformation+fact%2Dchecking%2E+In+Findings+of+the+Associati)
15. Marta Hasny, Maxime Di Folco, Keno Bressem, and Julia Schnabel. 2025. Tgv: Tabular data-guided learning of visual cardiac representations. arXiv preprint arXiv:2503.14998. — [arXiv:2503.14998](https://arxiv.org/abs/2503.14998) [find](https://scholar.google.com/scholar?q=Marta+Hasny%2C+Maxime+Di+Folco%2C+Keno+Bressem%2C+and+Julia+Schnabel%2E+2025%2E+Tgv%3A+Tabular+data%2Dguided+learning+of+visual+cardiac+representations%2E+arXiv+preprint+arXiv%3A2503%2E14998%2E+%E2%80%94+%5BarXiv%3A2503%2E14998%5D%28https%3A%2F)
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. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. 2014. [Learning to solve arithmetic word problems with verb categorization](https://md.research.elamur.ai/free/en/papers/hosseini-2014-learning-solve-arithmetic-word-problems/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 523–533.
18. Chen Huang, Xinwei Yang, Yang Deng, Wenqiang Lei, JianCheng Lv, and Tat-Seng Chua. 2024. Co-matching: Towards human-machine collaborative legal case matching. arXiv preprint arXiv:2405.10248. — [arXiv:2405.10248](https://arxiv.org/abs/2405.10248) [find](https://scholar.google.com/scholar?q=Chen+Huang%2C+Xinwei+Yang%2C+Yang+Deng%2C+Wenqiang+Lei%2C+JianCheng+Lv%2C+and+Tat%2DSeng+Chua%2E+2024%2E+Co%2Dmatching%3A+Towards+human%2Dmachine+collaborative+legal+case+matching%2E+arXiv+preprint+arXiv%3A2405%2E10248%2E+%E2%80%94+%5BarXiv)
19. Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, and Zhi Wang. 2026. Semantic-space exploration and exploitation in rlvr for llm reasoning. Preprint, arXiv:2509.23808. [find](https://scholar.google.com/scholar?q=Fanding+Huang%2C+Guanbo+Huang%2C+Xiao+Fan%2C+Yi+He%2C+Xiao+Liang%2C+Xiao+Chen%2C+Qinting+Jiang%2C+Faisal+Nadeem+Khan%2C+Jingyan+Jiang%2C+and+Zhi+Wang%2E+2026%2E+Semantic%2Dspace+exploration+and+exploitation+in+rlvr+for+llm+r)
20. Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, and 1 others. 2021. Ait-qa: Question answering dataset over complex tables in the airline industry. arXiv:2106.12944. arXiv preprint… [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+2021%2E+Ait%2Dqa%3A+Ques)
21. Zenan Li, Zhi Zhou, Yuan Yao, Yu-Feng Li, Chun Cao, Fan Yang, Xian Zhang, and Xiaoxing Ma. 2024a. Neuro-symbolic data generation for math reasoning. arXiv preprint arXiv:2412.04857. [find](https://scholar.google.com/scholar?q=Zenan+Li%2C+Zhi+Zhou%2C+Yuan+Yao%2C+Yu%2DFeng+Li%2C+Chun+Cao%2C+Fan+Yang%2C+Xian+Zhang%2C+and+Xiaoxing+Ma%2E+2024a%2E+Neuro%2Dsymbolic+data+generation+for+math+reasoning%2E+arXiv+preprint+arXiv%3A2412%2E04857%2E)
22. Zenan Li, Zhi Zhou, Yuan Yao, Xian Zhang, Yu-Feng Li, Chun Cao, Fan Yang, and Xiaoxing Ma. 2024b. Neuro-symbolic data generation for math reasoning. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Zenan+Li%2C+Zhi+Zhou%2C+Yuan+Yao%2C+Xian+Zhang%2C+Yu%2DFeng+Li%2C+Chun+Cao%2C+Fan+Yang%2C+and+Xiaoxing+Ma%2E+2024b%2E+Neuro%2Dsymbolic+data+generation+for+math+reasoning%2E+In+Advances+in+Neural+Information+Processing+System)
23. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+and+1+others%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412)
24. Pan Lu, Liang Qiu, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, and Ashwin Kalyan. 2023. [Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning](https://md.research.elamur.ai/free/en/papers/lu-2022-dynamic-prompt-learning-policy-gradient/). In The Eleventh International Conference on Learning Representations.
25. Weijian Ma, Shizhao Sun, Tianyu Yu, Ruiyu Wang, Tat-Seng Chua, and Jiang Bian. 2026. Thinking with blueprints: Assisting vision-language models in spatial reasoning via structured object representation. Preprint, arXiv:2601.01984. — [arXiv:2601.01984](https://arxiv.org/abs/2601.01984) [find](https://scholar.google.com/scholar?q=Weijian+Ma%2C+Shizhao+Sun%2C+Tianyu+Yu%2C+Ruiyu+Wang%2C+Tat%2DSeng+Chua%2C+and+Jiang+Bian%2E+2026%2E+Thinking+with+blueprints%3A+Assisting+vision%2Dlanguage+models+in+spatial+reasoning+via+structured+object+representatio)
26. Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, and Mehrdad Farajtabar. 2024. [Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models](https://md.research.elamur.ai/free/en/papers/mirzadeh-2024-gsm-symbolic-understanding-limitations-mathematical/). arXiv preprint arXiv:2410.05229.
27. OpenAI. 2023. Gpt-4. Technical report. — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/)
28. Ankur P Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. [Totto: A controlled table-to-text generation dataset](https://md.research.elamur.ai/free/en/papers/parikh-2020-totto-controlled-table-text-generation/). arXiv preprint arXiv:2004.14373.
29. 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/). arXiv preprint arXiv:1508.00305.
30. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) arXiv preprint arXiv:2103.07191.
31. Ziqiao Shang, Lingyue Ge, Yang Chen, Shi-Yu Tian, Zhenyu Huang, Wenbo Fu, Yu-Feng Li, and Lan-Zhe Guo. 2026. Maptab: Can mllms master constrained route planning? arXiv preprint arXiv:2602.18600. — [arXiv:2602.18600](https://arxiv.org/abs/2602.18600) [find](https://scholar.google.com/scholar?q=Ziqiao+Shang%2C+Lingyue+Ge%2C+Yang+Chen%2C+Shi%2DYu+Tian%2C+Zhenyu+Huang%2C+Wenbo+Fu%2C+Yu%2DFeng+Li%2C+and+Lan%2DZhe+Guo%2E+2026%2E+Maptab%3A+Can+mllms+master+constrained+route+planning%3F+arXiv+preprint+arXiv%3A2602%2E18600%2E+%E2%80%94+%5Bar)
32. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
33. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed Chi, Nathanael Schärli, and Denny Zhou. 2023. [Large language models can be easily distracted by irrelevant context](https://md.research.elamur.ai/free/en/papers/shi-2023-large-language-models-easily-distracted/). arXiv preprint arXiv:2302.00093.
34. Shi-Yu Tian, Zhi Zhou, Xin Su, and Yu-Feng Li. 2025a. Rethinking evaluation for multi-label drug-drug interaction prediction. Frontiers of Computer Science, 19(9):199358. [find](https://scholar.google.com/scholar?q=Shi%2DYu+Tian%2C+Zhi+Zhou%2C+Xin+Su%2C+and+Yu%2DFeng+Li%2E+2025a%2E+Rethinking+evaluation+for+multi%2Dlabel+drug%2Ddrug+interaction+prediction%2E+Frontiers+of+Computer+Science%2C+19%289%29%3A199358%2E)
35. Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu, Ming Yang, Lin-Han Jia, Lan-Zhe Guo, and Yu-Feng Li. 2025b. Vcsearch: Bridging the gap between well-defined and ill-defined problems in mathematical reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 12721–1… [find](https://scholar.google.com/scholar?q=Shi%2DYu+Tian%2C+Zhi+Zhou%2C+Kun%2DYang+Yu%2C+Ming+Yang%2C+Lin%2DHan+Jia%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+2025b%2E+Vcsearch%3A+Bridging+the+gap+between+well%2Ddefined+and+ill%2Ddefined+problems+in+mathematical+reasoning%2E+In+P)
36. Shiyu Tian, Hongxin Wei, Yiqun Wang, and Lei Feng. 2024. Crosel: Cross selection of confident pseudo labels for partial-label learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19479–19488. [find](https://scholar.google.com/scholar?q=Shiyu+Tian%2C+Hongxin+Wei%2C+Yiqun+Wang%2C+and+Lei+Feng%2E+2024%2E+Crosel%3A+Cross+selection+of+confident+pseudo+labels+for+partial%2Dlabel+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and)
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems, pages 24824–24837.
38. Xianjie Wu, Jian Yang, Linzheng Chai, Ge Zhang, Jiaheng Liu, Xeron Du, Di Liang, Daixin Shu, Xianfu Cheng, Tianzhen Sun, and 1 others. 2025. Tablebench: A comprehensive and complex benchmark for table question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pa… [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+2025%2E+Tablebench%3A+A+comprehensive+and+complex+benchmark+for+table)
39. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2024a. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+and+1+others%2E+2024a%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E1511)
40. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, and 1 others. 2024b. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.12122. — [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://md.research.elamur.ai/free/en/papers/yang-2024-qwen2-5-math-technical-report/)
41. Ming Yang, Zhi Zhou, Shi-Yu Tian, Kun-Yang Yu, Lan-Zhe Guo, and Yu-Feng Li. 2026. Nesy-route: A neuro-symbolic benchmark for constrained route planning in remote sensing. arXiv preprint arXiv:2603.16307. — [arXiv:2603.16307](https://arxiv.org/abs/2603.16307) [find](https://scholar.google.com/scholar?q=Ming+Yang%2C+Zhi+Zhou%2C+Shi%2DYu+Tian%2C+Kun%2DYang+Yu%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+2026%2E+Nesy%2Droute%3A+A+neuro%2Dsymbolic+benchmark+for+constrained+route+planning+in+remote+sensing%2E+arXiv+preprint+arXiv%3A2603%2E163)
42. Xinwei Yang, Zhaofeng Liu, Chen Huang, Jiashuai Zhang, Tong Zhang, Yifan Zhang, and Wenqiang Lei. 2025. Elaboration: A comprehensive benchmark on human-llm competitive programming. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag… [find](https://scholar.google.com/scholar?q=Xinwei+Yang%2C+Zhaofeng+Liu%2C+Chen+Huang%2C+Jiashuai+Zhang%2C+Tong+Zhang%2C+Yifan+Zhang%2C+and+Wenqiang+Lei%2E+2025%2E+Elaboration%3A+A+comprehensive+benchmark+on+human%2Dllm+competitive+programming%2E+In+Proceedings+of+t)
43. Kun-Yang Yu, Zhi Zhou, Shi-Yu Tian, Xiao-Wen Yang, Zi-Yi Jia, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo, and Yu-Feng Li. 2026. Thinking with tables: Enhancing multi-modal tabular understanding via neuro-symbolic reasoning. arXiv preprint arXiv:2603.24004. — [arXiv:2603.24004](https://arxiv.org/abs/2603.24004) [find](https://scholar.google.com/scholar?q=Kun%2DYang+Yu%2C+Zhi+Zhou%2C+Shi%2DYu+Tian%2C+Xiao%2DWen+Yang%2C+Zi%2DYi+Jia%2C+Ming+Yang%2C+Zi%2DJian+Cheng%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+2026%2E+Thinking+with+tables%3A+Enhancing+multi%2Dmodal+tabular+understanding+via+neuro%2Ds)
44. Elias Zavitsanos, Dimitris Mavroeidis, Eirini Spyropoulou, Manos Fergadiotis, and Georgios Paliouras. 2024. Entrant: A large financial dataset for table understanding. Scientific Data, 11(1):876. [find](https://scholar.google.com/scholar?q=Elias+Zavitsanos%2C+Dimitris+Mavroeidis%2C+Eirini+Spyropoulou%2C+Manos+Fergadiotis%2C+and+Georgios+Paliouras%2E+2024%2E+Entrant%3A+A+large+financial+dataset+for+table+understanding%2E+Scientific+Data%2C+11%281%29%3A876%2E)
45. Liangyu Zha, Junlin Zhou, Liyao Li, Rui Wang, Qingyi Huang, Saisai Yang, Jing Yuan, Changbao Su, Xiang Li, Aofeng Su, and 1 others. 2023. Tablegpt: Towards unifying tables, nature language and commands into one gpt. arXiv preprint arXiv:2307.08674. — [arXiv:2307.08674](https://arxiv.org/abs/2307.08674) [find](https://scholar.google.com/scholar?q=Liangyu+Zha%2C+Junlin+Zhou%2C+Liyao+Li%2C+Rui+Wang%2C+Qingyi+Huang%2C+Saisai+Yang%2C+Jing+Yuan%2C+Changbao+Su%2C+Xiang+Li%2C+Aofeng+Su%2C+and+1+others%2E+2023%2E+Tablegpt%3A+Towards+unifying+tables%2C+nature+language+and+command)
46. Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, and 1 others. 2024. Tablellm: Enabling tabular data manipulation by llms in real office usage scenarios. arXiv preprint arXiv:2403.19318. [find](https://scholar.google.com/scholar?q=Xiaokang+Zhang%2C+Sijia+Luo%2C+Bohan+Zhang%2C+Zeyao+Ma%2C+Jing+Zhang%2C+Yang+Li%2C+Guanlin+Li%2C+Zijun+Yao%2C+Kangli+Xu%2C+Jinchang+Zhou%2C+and+1+others%2E+2024%2E+Tablellm%3A+Enabling+tabular+data+manipulation+by+llms+in+real)
47. Jun Zhao, Jingqi Tong, Yurong Mou, Ming Zhang, Qi Zhang, and Xuan-Jing Huang. 2024. Exploring the compositional deficiency of large language models in mathematical reasoning through trap problems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16361–… [find](https://scholar.google.com/scholar?q=Jun+Zhao%2C+Jingqi+Tong%2C+Yurong+Mou%2C+Ming+Zhang%2C+Qi+Zhang%2C+and+Xuan%2DJing+Huang%2E+2024%2E+Exploring+the+compositional+deficiency+of+large+language+models+in+mathematical+reasoning+through+trap+problems%2E+In+)
48. Zhi Zhou, Ming Yang, Jiang-Xin Shi, Lan-Zhe Guo, and Yu-Feng Li. Decoop: Robust prompt tuning with out-of-distribution detection. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Zhi+Zhou%2C+Ming+Yang%2C+Jiang%2DXin+Shi%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+Decoop%3A+Robust+prompt+tuning+with+out%2Dof%2Ddistribution+detection%2E+In+Forty%2Dfirst+International+Conference+on+Machine+Learning%2E)
49. Zhi Zhou, Kun-Yang Yu, Lan-Zhe Guo, and Yu-Feng Li. 2025a. Fully test-time adaptation for tabular data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23027–23035. [find](https://scholar.google.com/scholar?q=Zhi+Zhou%2C+Kun%2DYang+Yu%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+2025a%2E+Fully+test%2Dtime+adaptation+for+tabular+data%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+39%2C+pages+23027%E2%80%9323035%2E)
50. Zhi Zhou, Kun-Yang Yu, Shi-Yu Tian, Xiao-Wen Yang, Jiang-Xin Shi, Pengxiao Song, Yi-Xuan Jin, Lan-Zhe Guo, and Yu-Feng Li. 2025b. Lawgpt: Knowledge-guided data generation and its application to legal llm. arXiv preprint arXiv:2502.06572. [find](https://scholar.google.com/scholar?q=Zhi+Zhou%2C+Kun%2DYang+Yu%2C+Shi%2DYu+Tian%2C+Xiao%2DWen+Yang%2C+Jiang%2DXin+Shi%2C+Pengxiao+Song%2C+Yi%2DXuan+Jin%2C+Lan%2DZhe+Guo%2C+and+Yu%2DFeng+Li%2E+2025b%2E+Lawgpt%3A+Knowledge%2Dguided+data+generation+and+its+application+to+legal+)
51. Zihao Zhou, Qiufeng Wang, Mingyu Jin, Jie Yao, Jianan Ye, Wei Liu, Wei Wang, Xiaowei Huang, and Kaizhu Huang. 2024. Mathattack: Attacking large language models towards math solving ability. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19750–19758. [find](https://scholar.google.com/scholar?q=Zihao+Zhou%2C+Qiufeng+Wang%2C+Mingyu+Jin%2C+Jie+Yao%2C+Jianan+Ye%2C+Wei+Liu%2C+Wei+Wang%2C+Xiaowei+Huang%2C+and+Kaizhu+Huang%2E+2024%2E+Mathattack%3A+Attacking+large+language+models+towards+math+solving+ability%2E+In+Proceed)
52. Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, and Tat-Seng Chua. 2021. [Tat-qa: A question answering benchmark on a hybrid of tabular and textual content in finance](https://md.research.elamur.ai/free/en/papers/zhu-2021-tat-qa-question-answering-benchmark/). arXiv preprint arXiv:2105.07624.
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)

*Updated 1 November 2026*