---
title: "Table Meets LLM — paper by Sui et al. (2023)"
description: "Based on these findings, the authors propose self-augmented prompting. 42 references, cited by 87 papers here."
authors: ["Yuan Sui", "Mengyu Zhou", "Mingjie Zhou", "Shi Han", "Dongmei Zhang"]
year: 2023
venue: "arXiv:2305.13062"
source: "https://arxiv.org/abs/2305.13062"
doi: "10.48550/arxiv.2305.13062"
arxiv: "2305.13062"
licence: "CC BY-NC-SA 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by-nc-sa/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sui-2023-table-meets-llm-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sui-2023-table-meets-llm-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/4/) / Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

# Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

**Authors:** [Yuan Sui](https://md.research.elamur.ai/free/en/authors/yuan-sui/), [Mengyu Zhou](https://md.research.elamur.ai/free/en/authors/mengyu-zhou/), Mingjie Zhou, [Shi Han](https://md.research.elamur.ai/free/en/authors/shi-han/) and [Dongmei Zhang](https://md.research.elamur.ai/free/en/authors/dongmei-zhang/) · **Year:** 2023 · **Venue:** [arXiv:2305.13062](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-web-search-and-data-mining-wsdm/) ([WSDM 2023](https://md.research.elamur.ai/free/en/venues/acm-international-conference-on-web-search-and-data-mining-wsdm/2023/)) · **Licence:** [CC BY-NC-SA 4.0 (arXiv)](http://creativecommons.org/licenses/by-nc-sa/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2305.13062) · [PDF](https://arxiv.org/pdf/2305.13062) · [DOI 10.48550/arxiv.2305.13062](https://doi.org/10.48550/arxiv.2305.13062) · [arXiv 2305.13062](https://arxiv.org/abs/2305.13062) · [OpenAlex](https://openalex.org/W4392366650)

**Citations:** 148 citations (OpenAlex, 2026-10-14) · [87](https://md.research.elamur.ai/free/en/papers/sui-2023-table-meets-llm-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

Large language models are often given tables flattened into text, but it is unclear whether they actually grasp table structure, and earlier work chose serialization formats in an inconsistent, ad hoc way. Sui et al. (Microsoft Research Asia; WSDM '24) introduce SUC, a benchmark of seven structure-focused tasks, including cell lookup, row retrieval and table size detection. They use it to test GPT-3.5 and GPT-4 under different input designs: serialization format, content order, role prompting, partition marks, format explanations, and zero-shot versus one-shot setups.

The results show that both models have some structural understanding but remain unreliable, failing even on simple tasks such as counting rows and columns. Input choices also produce clear performance gaps, and these persist with GPT-4. Based on these findings, the authors propose self-augmented prompting. In this two-step approach, the model first produces its own structural cues, such as key values or ranges, and then answers the task. Combined with HTML-style markup, this improves results on five downstream datasets. The work offers practical guidance for anyone feeding tabular data to LLMs.

## Key points

- **SUC benchmark:** contains seven tasks probing structural understanding (for example cell lookup, row retrieval and size detection). It was evaluated on GPT-3.5 and GPT-4, and code and data are planned for github.com/microsoft/TableProvider.
- **Recommended input design:** markup such as HTML, plus a format explanation and partition marks.
- **Gains from self-augmented prompting over baselines:** TabFact +2.31%, HybridQA +2.13%, SQA +2.72%, Feverous +0.84% and ToTTo +5.68%.
- **Most effective self-generated cue:** having the model identify key ranges and values gave an overall 3.26% improvement over plain one-shot prompting. Removing the manual table-size hint lowered results by only about 0.4%.
- **Manual versus self-generated explanations:** on FEVEROUS, whose tables are irregular and contain sub-tables, hand-written format explanations could hurt performance, while self-generated ones were more detailed and more helpful.

*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

- [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) — University, Singapore, Singapore · 207 works · 39,576 citations
- [Microsoft Research Asia](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) — Company, Beijing, China · 82 works · 61,484 citations
- [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) — University, Pok Fu Lam, China · 118 works · 13,496 citations

📚 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): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works

## Cite

Cite as: Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han and Dongmei Zhang. 2023. Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study. arXiv:2305.13062.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{sui2023table,
  title = {{Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study}},
  author = {Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han and Dongmei Zhang},
  year = {2023},
  doi = {10.48550/arxiv.2305.13062},
  eprint = {2305.13062},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.13062}
}
```

- [← previous Detecting and Preventing Hallucinations in Large Vision Language Models](https://md.research.elamur.ai/free/en/papers/gunjal-2023-detecting-preventing-hallucinations-large-vision/)
- [next → Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://md.research.elamur.ai/free/en/papers/kamalloo-2023-evaluating-open-domain-question-answering/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/4/)

## References

42 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pranjal Aggarwal, Aman Madaan, Yiming Yang, and Mausam. 2023. Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs. https://doi.org/10.48550/arXiv.2305.11860 arXiv:2305.11860 [cs] — [doi:10.48550/arxiv.2305.11860](https://doi.org/10.48550/arxiv.2305.11860) [↗](https://doi.org/10.48550/arXiv.2305.11860)
2. Armen Aghajanyan, Dmytro Okhonko, Mike Lewis, Mandar Joshi, Hu Xu, Gargi Ghosh, and Luke Zettlemoyer. 2021. HTLM: Hyper-Text Pre-Training and Prompting of Language Models. arXiv:2107.06955 [cs] http://arxiv.org/abs/2107.06955 [↗](http://arxiv.org/abs/2107.06955)
3. Rami Aly, Zhijiang Guo, Michael Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, and Arpit Mittal. 2021. FEVER-OUS: Fact Extraction and VERification Over Unstructured and Structured Information. https://doi.org/10.48550/arXiv.2106.05707 arXiv:2106.05707 [cs] — [doi:10.48550/arxiv.2106.05707](https://doi.org/10.48550/arxiv.2106.05707) [↗](https://doi.org/10.48550/arXiv.2106.05707)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Dhariwal, et al. 2020. [Language Models Are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 1877–1901. [https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bf…](https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bf…) [↗](https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bf…)
5. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Kaplan, et al. 2021. [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). https://doi.org/10.48550/arXiv.2107.03374 arXiv:2107.03374 [cs] [↗](https://doi.org/10.48550/arXiv.2107.03374)
6. Wenhu Chen. 2022. [Large Language Models Are Few(1)-Shot Table Reasoners](https://md.research.elamur.ai/free/en/papers/chen-2023-large-language-models-are-few/). https://doi.org/10.48550/arXiv.2210.06710 arXiv:2210.06710 [cs] [↗](https://doi.org/10.48550/arXiv.2210.06710)
7. Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, and William Yang Wang. 2020. [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/). https://doi.org/10.48550/arXiv.1909.02164 arXiv:1909.02164 [cs] [↗](https://doi.org/10.48550/arXiv.1909.02164)
8. Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, and William Yang Wang. 2020. [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://md.research.elamur.ai/free/en/papers/chen-2020-hybridqa-dataset-multi-hop-question/). In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, Online, 10…
9. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan… [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Yunxuan+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+Albert+Webson%2C+Shixiang+Shane+Gu%2C+Zhuyun+Dai%2C+Mirac+Suzgun%2C+X)
10. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training Verifiers to Solve Math Word Problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). https://doi.org/10.48550/arXiv.2110.14168 arXiv:2110.1416… [↗](https://doi.org/10.48550/arXiv.2110.14168)
11. Xiang Deng, Huan Sun, Alyssa Lees, You Wu, and Cong Yu. 2020. TURL: Table Understanding through Representation Learning. https://doi.org/10.48550/arXiv.2006.14806 arXiv:2006.14806 [cs] — [doi:10.48550/arxiv.2006.14806](https://doi.org/10.48550/arxiv.2006.14806) [↗](https://doi.org/10.48550/arXiv.2006.14806)
12. Haoyu Dong, Zhoujun Cheng, Xinyi He, Mengyu Zhou, Anda Zhou, Fan Zhou, Ao Liu, Shi Han, and Dongmei Zhang. 2022. Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks. https://doi.org/10.48550/arXiv.2201.09745 arXiv:2201.09745 [cs] — [doi:10.48550/arxiv.2201.09745](https://doi.org/10.48550/arxiv.2201.09745) [↗](https://doi.org/10.48550/arXiv.2201.09745)
13. Longxu Dou, Yan Gao, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, and Jian-Guang Lou. 2022. UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL. arXiv:2203.07781 [cs] http://arxiv.org/abs/2203.07781 — [arXiv:2203.07781](https://arxiv.org/abs/2203.07781) [↗](http://arxiv.org/abs/2203.07781)
14. Julian Martin Eisenschlos, Maharshi Gor, Thomas Müller, and William W. Cohen. 2021. MATE: Multi-View Attention for Table Transformer Efficiency. https://doi.org/10.48550/arXiv.2109.04312 arXiv:2109.04312 [cs] [↗](https://doi.org/10.48550/arXiv.2109.04312)
15. Björn Engelmann, Timo Breuer, and Philipp Schaer. 2023. Simulating Users in Interactive Web Table Retrieval. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (Birmingham, United Kingdom) (CIKM ’23). Association for Computing Machinery, New York, NY, USA… — [doi:10.1145/3583780.3615187](https://doi.org/10.1145/3583780.3615187) [find](https://scholar.google.com/scholar?q=Bj%C3%B6rn+Engelmann%2C+Timo+Breuer%2C+and+Philipp+Schaer%2E+2023%2E+Simulating+Users+in+Interactive+Web+Table+Retrieval%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Information+and+Knowledge+Manage)
16. Heng Gong, Yawei Sun, Xiaocheng Feng, Bing Qin, Wei Bi, Xiaojiang Liu, and Ting Liu. 2020. TableGPT: Few-Shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee o… [find](https://scholar.google.com/scholar?q=Heng+Gong%2C+Yawei+Sun%2C+Xiaocheng+Feng%2C+Bing+Qin%2C+Wei+Bi%2C+Xiaojiang+Liu%2C+and+Ting+Liu%2E+2020%2E+TableGPT%3A+Few%2DShot+Table%2Dto%2DText+Generation+with+Table+Structure+Reconstruction+and+Content+Matching%2E+In+Proc)
17. Xinyi He, Mengyu Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, and Dongmei Zhang. 2022. Inferring Tabular Analysis Metadata by Infusing Distribution and Knowledge Information. https://doi.org/10.48550/arXiv.2209.00946 arXiv:2209.00946 [cs] — [doi:10.48550/arxiv.2209.00946](https://doi.org/10.48550/arxiv.2209.00946) [↗](https://doi.org/10.48550/arXiv.2209.00946)
18. Jonathan Herzig, Pawel Krzysztof Nowak, Thomas Müller, Francesco Piccinno, and Julian Eisenschlos. 2020. [TaPas: Weakly Supervised Table Parsing via Pre-Training](https://md.research.elamur.ai/free/en/papers/herzig-2020-tapas-weakly-supervised-table-parsing/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Onl…
19. Madelon Hulsebos, Çağatay Demiralp, and Paul Groth. 2022. GitTables: A Large-Scale Corpus of Relational Tables. https://doi.org/10.48550/arXiv.2106.07258 arXiv:2106.07258 [cs] — [doi:10.48550/arxiv.2106.07258](https://doi.org/10.48550/arxiv.2106.07258) [↗](https://doi.org/10.48550/arXiv.2106.07258)
20. Hiroshi Iida, Dung Thai, Varun Manjunatha, and Mohit Iyyer. 2021. [TABBIE: Pretrained Representations of Tabular Data](https://md.research.elamur.ai/free/en/papers/iida-2021-tabbie-pretrained-representations-tabular-data/). https://doi.org/10.48550/arXiv.2105.02584 arXiv:2105.02584 [cs] [↗](https://doi.org/10.48550/arXiv.2105.02584)
21. 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). Association for Computational Linguistics, Vancouver, Can…
22. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large Language Models Are Zero-Shot Reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). https://doi.org/10.48550/arXiv.2205.11916 arXiv:2205.11916 [cs] [↗](https://doi.org/10.48550/arXiv.2205.11916)
23. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://md.research.elamur.ai/free/en/papers/lin-2022-truthfulqa-measuring-how-models-mimic/). arXiv:2109.07958 [cs] http://arxiv.org/abs/2109.07958 [↗](http://arxiv.org/abs/2109.07958)
24. Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, Ronan Le Bras, Yejin Choi, and Hannaneh Hajishirzi. 2022. Generated Knowledge Prompting for Commonsense Reasoning. https://doi.org/10.48550/arXiv.2110.08387 arXiv:2110.08387 [cs] [↗](https://doi.org/10.48550/arXiv.2110.08387)
25. Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, and Jian-Guang Lou. 2022. [TAPEX: Table Pre-Training via Learning a Neural SQL Executor](https://md.research.elamur.ai/free/en/papers/liu-2021-tapex-table-pre-training-learning/). https://doi.org/10.48550/arXiv.2107.07653 arXiv:2107.07653 [cs] [↗](https://doi.org/10.48550/arXiv.2107.07653)
26. Ahmed Nassar, Nikolaos Livathinos, Maksym Lysak, and Peter Staar. 2022. Table-Former: Table Structure Understanding with Transformers. https://doi.org/10.48550/arXiv.2203.01017 arXiv:2203.01017 [cs] — [doi:10.48550/arxiv.2203.01017](https://doi.org/10.48550/arxiv.2203.01017) [↗](https://doi.org/10.48550/arXiv.2203.01017)
27. OpenAI. 2023. [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). https://doi.org/10.48550/arXiv.2303.08774 arXiv:2303.08774 [cs] [↗](https://doi.org/10.48550/arXiv.2303.08774)
28. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
29. 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/). https://doi.org/10.48550/arXiv.2004.14373 arXiv:2004.14373 [cs] [↗](https://doi.org/10.48550/arXiv.2004.14373)
30. Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Song, et al. 2022. Scaling Language Models: Methods, Analysis & Insights from Training Gopher. https://doi.org/10.48550/arXiv.2112.11446 arXiv:2112.11446 [cs] [↗](https://doi.org/10.48550/arXiv.2112.11446)
31. Yijia Shao, Mengyu Zhou, Yifan Zhong, Tao Wu, Hongwei Han, Shi Han, Gideon Huang, and Dongmei Zhang. 2022. FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information. https://doi.org/10.48550/arXiv.2211.05284 arXiv:2211.05284 [cs] [↗](https://doi.org/10.48550/arXiv.2211.05284)
32. Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant. 2021. MultiModalQA: Complex Question Answering over Text, Tables and Images. https://doi.org/10.48550/arXiv.2104.06039 arXiv:2104.06039 [cs] — [doi:10.48550/arxiv.2104.06039](https://doi.org/10.48550/arxiv.2104.06039) [↗](https://doi.org/10.48550/arXiv.2104.06039)
33. Yi Tay, Mostafa Dehghani, Dara Bahri, and Donald Metzler. 2022. [Efficient Transformers: A Survey](https://md.research.elamur.ai/free/en/papers/tay-2020-efficient-transformers-survey/). https://doi.org/10.48550/arXiv.2009.06732 arXiv:2009.06732 [cs] [↗](https://doi.org/10.48550/arXiv.2009.06732)
34. Mohamed Trabelsi, Zhiyu Chen, Shuo Zhang, Brian D. Davison, and Jeff Heflin. 2022. StruBERT: Structure-aware BERT for Table Search and Matching. In Proceedings of the ACM Web Conference 2022. ACM. https://doi.org/10.1145/3485447.3511972 — [doi:10.1145/3485447.3511972](https://doi.org/10.1145/3485447.3511972) [↗](https://doi.org/10.1145/3485447.3511972)
35. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention Is All You Need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc. [https://proceedings.neurips.cc/paper/2017/hash/3f5ee243…](https://proceedings.neurips.cc/paper/2017/hash/3f5ee243…) [↗](https://proceedings.neurips.cc/paper/2017/hash/3f5ee243…)
36. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). https://doi.org/10.48550/arXiv.2203.11171 arXiv:2203.11171 [cs] [↗](https://doi.org/10.48550/arXiv.2203.11171)
37. Zhiruo Wang, Haoyu Dong, Ran Jia, Jia Li, Zhiyi Fu, Shi Han, and Dongmei Zhang. 2021. TUTA: Tree-Based Transformers for Generally Structured Table Pre-Training. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1780–1790. https://doi.org/10.1145/3447548.3467434 a… — [doi:10.1145/3447548.3467434](https://doi.org/10.1145/3447548.3467434) [↗](https://doi.org/10.1145/3447548.3467434)
38. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc 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/). https://doi.org/10.48550/arXiv.2201.11903 arXiv:2201.11903 [cs] [↗](https://doi.org/10.48550/arXiv.2201.11903)
39. Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zett… — [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://md.research.elamur.ai/free/en/papers/xie-2022-unifiedskg-unifying-multi-tasking-structured/)
40. Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://md.research.elamur.ai/free/en/papers/yin-2020-tabert-pretraining-joint-understanding-textual/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8413–8426. ht…
41. Shuo Zhang and Krisztian Balog. 2020. Web Table Extraction, Retrieval and Augmentation: A Survey. https://doi.org/10.48550/ARXIV.2002.00207 — [doi:10.48550/arxiv.2002.00207](https://doi.org/10.48550/arxiv.2002.00207) [↗](https://doi.org/10.48550/ARXIV.2002.00207)
42. Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, and Chuang Gan. 2023. [Planning with Large Language Models for Code Generation](https://md.research.elamur.ai/free/en/papers/zhang-2023-planning-large-language-models-code/). https://doi.org/10.48550/arXiv.2303.05510 arXiv:2303.05510 [cs] [↗](https://doi.org/10.48550/arXiv.2303.05510)

*Updated 2 November 2026*