---
title: "CORES — paper by Zhang et al. (2026) — summary and ideas"
description: "The authors also build ProcQA, a training and evaluation set of aligned Python–SQL pairs. 48 references."
authors: ["Meng Zhang", "Ruochun Jin", "Yuanxi Peng", "Wenjing Yang", "Haotian Wang", "Liting Sun", "Kun Hu", "Silin Yang", "Zhang Ke-di"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.237/"
doi: "10.18653/v1/2026.findings-acl.237"
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/zhang-2026-cores-code-oriented-reasoning-complex/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-cores-code-oriented-reasoning-complex/)

[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/28/) / CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA

# CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA

**Authors:** [Meng Zhang](https://md.research.elamur.ai/free/en/authors/meng-zhang/), [Ruochun Jin](https://md.research.elamur.ai/free/en/authors/ruochun-jin/), Yuanxi Peng, Wenjing Yang, [Haotian Wang](https://md.research.elamur.ai/free/en/authors/haotian-wang/), Liting Sun, Kun Hu, Silin Yang and Zhang Ke-di · **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.237/) · [PDF](https://aclanthology.org/2026.findings-acl.237.pdf) · [DOI 10.18653/v1/2026.findings-acl.237](https://doi.org/10.18653/v1/2026.findings-acl.237) · [OpenAlex](https://openalex.org/W7166850161)

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

## Summary
LLMs fine-tuned for text-to-SQL handle simple queries well but struggle with complex analytical questions that need multi-step logic, nested aggregation or arithmetic. They also tend to forget other skills. The authors show that SQL-specialised models such as OmniSQL-7B, SQL-R1-7B and Arctic-Text2SQL-R1-7B can effectively no longer write Python or give direct answers, which makes them weak at TableQA.

CORES addresses both problems by using Python as an intermediate reasoning step. Under the CoPS prompting scheme, the model first writes a procedural Python trace and only then produces the declarative SQL. This behaviour is trained with GRPO and a process-level reward that checks format, schema linking, logical structure and execution, giving denser feedback than an execution-only signal. The authors also build ProcQA, a training and evaluation set of aligned Python–SQL pairs.

The 3B and 7B models beat strong baselines on six text-to-SQL benchmarks and still perform well on TableQA. This matters for privacy-constrained settings where small models must run locally.

## Key points
- **ProcQA:** about 12k complex questions, each paired with verified, executable Python and SQL.
- **Text-to-SQL results:** average execution accuracy is 59.89% for CORES-7B and 49.91% for CORES-3B across six benchmarks, about 6.44% above leading baselines on average.
- **TableQA results (TableBench, HiTab, FinQA):** Python-generation accuracy recovers from roughly zero in SQL-tuned models to 51.40%. A hybrid rule that combines direct, Python and SQL answers gives CORES-3B a 9.35% gain on TableBench over its best single strategy.
- **Ablation on ProcQA (CORES-3B):** the full reward reaches 38.80 Proc-SQL and 27.07 Proc-PY. An execution-only reward reaches 35.80 and 24.87, and the untrained model reaches 23.07 and 13.00. Dropping the schema-linking reward mainly hurts SQL, while dropping the structure reward mainly hurts Python.
- **Limitations:** Python is the only intermediate language tested, and training uses text-to-SQL data only, so TableQA ability comes purely from generalization. Only 3B and 7B models are tested; the paper gives Qwen2.5-Coder-3B-Instruct as the 3B base. Code is available at github.com/mengzhang18/CORES.

*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

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 315 works · 43,267 citations
- [National University of Defense Technology](https://md.research.elamur.ai/free/en/universities/national-university-of-defense-technology/) — University, Changsha, China · 20 works · 1,339 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 Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 100 works

🧭 Topics (3): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [🧾 Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) · 193 works · [💻 Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · 168 works

## Cite

Cite as: Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang and Zhang Ke-di. 2026. CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA. 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{zhang2026cores,
  title = {{CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA}},
  author = {Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang and Zhang Ke-di},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.237},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.237}
}
```

- [← previous CoreGaze: Core Subgraph-Driven Visual Gaze Diffusion for Training-Free Referring Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/yi-2026-coregaze-core-subgraph-driven-visual/)
- [next → Corpas Náisiúnta Na Gaeilge 2022-2029: A Project Overview](https://md.research.elamur.ai/free/en/papers/meachair-2026-corpas-naisiunta-na-gaeilge-2022/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/)

## References

48 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Xueguang+Ma%2C+Xinyi+Wang%2C+and+William+W+Cohen%2E+2022%2E+Program+of+thoughts+prompting%3A+Disentangling+computation+from+reasoning+for+numerical+reasoning+tasks%2E+arXiv+preprint+arXiv%3A2211%2E12588%2E)
2. 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, pages 1026–1036.
3. 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…
4. Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, and Dongmei Zhang. 2022. [Hitab: A hierarchical table dataset for question answering and natural language generation](https://md.research.elamur.ai/free/en/papers/cheng-2021-hitab-hierarchical-table-dataset-question/). In Proceedings of the 60th annual meeting of the association for computational linguistic…
5. Yongdong Chi, Hanqing Wang, Yun Chen, Yan Yang, Jian Yang, Zonghan Yang, Xiao Yan, and Guanhua Chen. 2025. Pi-sql: Enhancing text-to-sql with fine-grained guidance from pivot programming languages. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25120–25144. [find](https://scholar.google.com/scholar?q=Yongdong+Chi%2C+Hanqing+Wang%2C+Yun+Chen%2C+Yan+Yang%2C+Jian+Yang%2C+Zonghan+Yang%2C+Xiao+Yan%2C+and+Guanhua+Chen%2E+2025%2E+Pi%2Dsql%3A+Enhancing+text%2Dto%2Dsql+with+fine%2Dgrained+guidance+from+pivot+programming+languages%2E+In)
6. Chris J Date. 2011. SQL and relational theory: how to write accurate SQL code. " O’Reilly Media, Inc.". [find](https://scholar.google.com/scholar?q=Chris+J+Date%2E+2011%2E+SQL+and+relational+theory%3A+how+to+write+accurate+SQL+code%2E+%22+O%E2%80%99Reilly+Media%2C+Inc%2E%22%2E)
7. Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, and Matthew Richardson. 2021. [Structure-grounded pretraining for text-to-sql](https://md.research.elamur.ai/free/en/papers/deng-2021-structure-grounded-pretraining-text-sql/). In The 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.
8. 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 preprint arXiv:2407.21783.
9. Dawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun, Yichen Qian, Bolin Ding, and Jingren Zhou. 2024. [Text-to-sql empowered by large language models: A benchmark evaluation](https://md.research.elamur.ai/free/en/papers/gao-2023-text-sql-empowered-large-language/). Proceedings of the VLDB Endowment, 17(5):1132–1145.
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 International Conference on Machine Learning, pages 10764–10799. PMLR. [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+International+Conference+on+Machine+Learning%2C+page)
11. Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, and Xiao Huang. 2024. Next-generation database interfaces: A survey of llm-based text-to-sql. arXiv preprint arXiv:2406.08426. — [arXiv:2406.08426](https://arxiv.org/abs/2406.08426) [find](https://scholar.google.com/scholar?q=Zijin+Hong%2C+Zheng+Yuan%2C+Qinggang+Zhang%2C+Hao+Chen%2C+Junnan+Dong%2C+Feiran+Huang%2C+and+Xiao+Huang%2E+2024%2E+Next%2Dgeneration+database+interfaces%3A+A+survey+of+llm%2Dbased+text%2Dto%2Dsql%2E+arXiv+preprint+arXiv%3A2406%2E084)
12. Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, and 1 others. 2025. [Opencoder: The open cookbook for top-tier code large language models](https://md.research.elamur.ai/free/en/papers/huang-2025-opencoder-open-cookbook-top-tier/). In Proceedings of the 63rd Annual Meeting of the Association for Computational…
13. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Keming Lu, and 1 others. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186. — [Qwen2.5-Coder Technical Report](https://md.research.elamur.ai/free/en/papers/hui-2024-qwen2-5-coder-technical-report/)
14. Ruochun Jin, Xiyue Wang, Dong Wang, Haoqi Zheng, Yunpeng Qi, Silin Yang, and Meng Zhang. 2025. Talon: A multi-agent framework for long-table exploration and question answering. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 27385–27401. [find](https://scholar.google.com/scholar?q=Ruochun+Jin%2C+Xiyue+Wang%2C+Dong+Wang%2C+Haoqi+Zheng%2C+Yunpeng+Qi%2C+Silin+Yang%2C+and+Meng+Zhang%2E+2025%2E+Talon%3A+A+multi%2Dagent+framework+for+long%2Dtable+exploration+and+question+answering%2E+In+Proceedings+of+the+2)
15. Rahul Kumar, Amar Raja Dibbu, Shrutendra Harsola, Vignesh Subrahmaniam, and Ashutosh Modi. 2024. Booksql: A large scale text-to-sql dataset for accounting domain. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech… [find](https://scholar.google.com/scholar?q=Rahul+Kumar%2C+Amar+Raja+Dibbu%2C+Shrutendra+Harsola%2C+Vignesh+Subrahmaniam%2C+and+Ashutosh+Modi%2E+2024%2E+Booksql%3A+A+large+scale+text%2Dto%2Dsql+dataset+for+accounting+domain%2E+In+Proceedings+of+the+2024+Conference)
16. Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, and Kang Liu. 2025. Reasoning-table: Exploring reinforcement learning for table reasoning. arXiv preprint arXiv:2506.01710. — [arXiv:2506.01710](https://arxiv.org/abs/2506.01710) [find](https://scholar.google.com/scholar?q=Fangyu+Lei%2C+Jinxiang+Meng%2C+Yiming+Huang%2C+Tinghong+Chen%2C+Yun+Zhang%2C+Shizhu+He%2C+Jun+Zhao%2C+and+Kang+Liu%2E+2025%2E+Reasoning%2Dtable%3A+Exploring+reinforcement+learning+for+table+reasoning%2E+arXiv+preprint+arXiv%3A)
17. Haoyang Li, Shang Wu, Xiaokang Zhang, Xinmei Huang, Jing Zhang, Fuxin Jiang, Shuai Wang, Tieying Zhang, Jianjun Chen, Rui Shi, and 1 others. 2025. Omnisql: Synthesizing high-quality text-to-sql data at scale. arXiv preprint arXiv:2503.02240. — [arXiv:2503.02240](https://arxiv.org/abs/2503.02240) [find](https://scholar.google.com/scholar?q=Haoyang+Li%2C+Shang+Wu%2C+Xiaokang+Zhang%2C+Xinmei+Huang%2C+Jing+Zhang%2C+Fuxin+Jiang%2C+Shuai+Wang%2C+Tieying+Zhang%2C+Jianjun+Chen%2C+Rui+Shi%2C+and+1+others%2E+2025%2E+Omnisql%3A+Synthesizing+high%2Dquality+text%2Dto%2Dsql+data+a)
18. Haoyang Li, Jing Zhang, Hanbing Liu, Ju Fan, Xiaokang Zhang, Jun Zhu, Renjie Wei, Hongyan Pan, Cuiping Li, and Hong Chen. 2024a. [Codes: Towards building open-source language models for text-to-sql](https://md.research.elamur.ai/free/en/papers/li-2024-codes-towards-building-open-source/). Proceedings of the ACM on Management of Data, 2(3):1–28.
19. Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, and 1 others. 2024b. [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.
20. Tao Liu, Hongying Zan, Yifan Li, Dixuan Zhang, Lulu Kong, Haixin Liu, Jiaming Hou, Aoze Zheng, Rui Li, Yiming Qiao, and 1 others. 2025a. Logiccat: A chain-of-thought text-to-sql benchmark for multi-domain reasoning challenges. arXiv preprint arXiv:2505.18744. — [arXiv:2505.18744](https://arxiv.org/abs/2505.18744) [find](https://scholar.google.com/scholar?q=Tao+Liu%2C+Hongying+Zan%2C+Yifan+Li%2C+Dixuan+Zhang%2C+Lulu+Kong%2C+Haixin+Liu%2C+Jiaming+Hou%2C+Aoze+Zheng%2C+Rui+Li%2C+Yiming+Qiao%2C+and+1+others%2E+2025a%2E+Logiccat%3A+A+chain%2Dof%2Dthought+text%2Dto%2Dsql+benchmark+for+multi%2Ddo)
21. Yifu Liu, Yin Zhu, Yingqi Gao, Zhiling Luo, Xiaoxia Li, Xiaorong Shi, Yuntao Hong, Jinyang Gao, Yu Li, Bolin Ding, and 1 others. 2025b. Xiyan-sql: A novel multi-generator framework for text-to-sql. arXiv preprint arXiv:2507.04701. — [arXiv:2507.04701](https://arxiv.org/abs/2507.04701) [find](https://scholar.google.com/scholar?q=Yifu+Liu%2C+Yin+Zhu%2C+Yingqi+Gao%2C+Zhiling+Luo%2C+Xiaoxia+Li%2C+Xiaorong+Shi%2C+Yuntao+Hong%2C+Jinyang+Gao%2C+Yu+Li%2C+Bolin+Ding%2C+and+1+others%2E+2025b%2E+Xiyan%2Dsql%3A+A+novel+multi%2Dgenerator+framework+for+text%2Dto%2Dsql%2E+ar)
22. Peixian Ma, Xialie Zhuang, Chengjin Xu, Xuhui Jiang, Ran Chen, and Jian Guo. 2025. Sql-r1: Training natural language to sql reasoning model by reinforcement learning. arXiv preprint arXiv:2504.08600. — [arXiv:2504.08600](https://arxiv.org/abs/2504.08600) [find](https://scholar.google.com/scholar?q=Peixian+Ma%2C+Xialie+Zhuang%2C+Chengjin+Xu%2C+Xuhui+Jiang%2C+Ran+Chen%2C+and+Jian+Guo%2E+2025%2E+Sql%2Dr1%3A+Training+natural+language+to+sql+reasoning+model+by+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2504%2E08600%2E+)
23. Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, and Graham Neubig. 2022. [Language models of code are few-shot commonsense learners](https://md.research.elamur.ai/free/en/papers/madaan-2022-language-models-code-few-shot/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1384–1403.
24. Mayank Mishra, Matt Stallone, Gaoyuan Zhang, Yikang Shen, Aditya Prasad, Adriana Meza Soria, Michele Merler, Parameswaran Selvam, Saptha Surendran, Shivdeep Singh, and 1 others. 2024. Granite code models: A family of open foundation models for code intelligence. arXiv preprint arXiv:2405.04324. [find](https://scholar.google.com/scholar?q=Mayank+Mishra%2C+Matt+Stallone%2C+Gaoyuan+Zhang%2C+Yikang+Shen%2C+Aditya+Prasad%2C+Adriana+Meza+Soria%2C+Michele+Merler%2C+Parameswaran+Selvam%2C+Saptha+Surendran%2C+Shivdeep+Singh%2C+and+1+others%2E+2024%2E+Granite+code+mod)
25. Simone Papicchio, Simone Rossi, Luca Cagliero, and Paolo Papotti. 2025. Think2sql: Reinforce llm reasoning capabilities for text2sql. arXiv preprint arXiv:2504.15077. [find](https://scholar.google.com/scholar?q=Simone+Papicchio%2C+Simone+Rossi%2C+Luca+Cagliero%2C+and+Paolo+Papotti%2E+2025%2E+Think2sql%3A+Reinforce+llm+reasoning+capabilities+for+text2sql%2E+arXiv+preprint+arXiv%3A2504%2E15077%2E)
26. Mohammadreza Pourreza and Davood Rafiei. 2024. [Din-sql: Decomposed in-context learning of text-to-sql with self-correction](https://md.research.elamur.ai/free/en/papers/pourreza-2023-din-sql-decomposed-context-learning/). Advances in Neural Information Processing Systems, 36.
27. Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, and 1 others. 2022. A survey on text-to-sql parsing: Concepts, methods, and future directions. arXiv preprint arXiv:2208.13629. — [arXiv:2208.13629](https://arxiv.org/abs/2208.13629) [find](https://scholar.google.com/scholar?q=Bowen+Qin%2C+Binyuan+Hui%2C+Lihan+Wang%2C+Min+Yang%2C+Jinyang+Li%2C+Binhua+Li%2C+Ruiying+Geng%2C+Rongyu+Cao%2C+Jian+Sun%2C+Luo+Si%2C+and+1+others%2E+2022%2E+A+survey+on+text%2Dto%2Dsql+parsing%3A+Concepts%2C+methods%2C+and+future+dire)
28. John W Ratcliff, David E Metzener, and 1 others. 1988. Pattern matching: The gestalt approach. Dr. Dobb’s Journal, 13(7):46. [find](https://scholar.google.com/scholar?q=John+W+Ratcliff%2C+David+E+Metzener%2C+and+1+others%2E+1988%2E+Pattern+matching%3A+The+gestalt+approach%2E+Dr%2E+Dobb%E2%80%99s+Journal%2C+13%287%29%3A46%2E)
29. 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.
30. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, pages 1279–1297.
31. Lei Sheng and Shuai-Shuai Xu. 2025. Csc-sql: Corrective self-consistency in text-to-sql via reinforcement learning. arXiv preprint arXiv:2505.13271. [find](https://scholar.google.com/scholar?q=Lei+Sheng+and+Shuai%2DShuai+Xu%2E+2025%2E+Csc%2Dsql%3A+Corrective+self%2Dconsistency+in+text%2Dto%2Dsql+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2505%2E13271%2E)
32. Aofeng Su, Aowen Wang, Chao Ye, Chen Zhou, Ga Zhang, Gang Chen, Guangcheng Zhu, Haobo Wang, Haokai Xu, Hao Chen, and 1 others. 2024. Tablegpt2: A large multimodal model with tabular data integration. arXiv preprint arXiv:2411.02059. — [arXiv:2411.02059](https://arxiv.org/abs/2411.02059) [find](https://scholar.google.com/scholar?q=Aofeng+Su%2C+Aowen+Wang%2C+Chao+Ye%2C+Chen+Zhou%2C+Ga+Zhang%2C+Gang+Chen%2C+Guangcheng+Zhu%2C+Haobo+Wang%2C+Haokai+Xu%2C+Hao+Chen%2C+and+1+others%2E+2024%2E+Tablegpt2%3A+A+large+multimodal+model+with+tabular+data+integration%2E+)
33. Yize Sui, Jing Ren, Wenjing Yang, Ruochun Jin, Liyang Xu, Xiyao Liu, and Ji Wang. 2025. Elastic robust unlearning of specific knowledge in large language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yize+Sui%2C+Jing+Ren%2C+Wenjing+Yang%2C+Ruochun+Jin%2C+Liyang+Xu%2C+Xiyao+Liu%2C+and+Ji+Wang%2E+2025%2E+Elastic+robust+unlearning+of+specific+knowledge+in+large+language+models%2E+In+The+Thirty%2Dninth+Annual+Conference+)
34. Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang, Azalia Mirhoseini, and Amin Saberi. 2024. Chess: Contextual harnessing for efficient sql synthesis. arXiv preprint arXiv:2405.16755. — [arXiv:2405.16755](https://arxiv.org/abs/2405.16755) [find](https://scholar.google.com/scholar?q=Shayan+Talaei%2C+Mohammadreza+Pourreza%2C+Yu%2DChen+Chang%2C+Azalia+Mirhoseini%2C+and+Amin+Saberi%2E+2024%2E+Chess%3A+Contextual+harnessing+for+efficient+sql+synthesis%2E+arXiv+preprint+arXiv%3A2405%2E16755%2E+%E2%80%94+%5BarXiv%3A2405%2E)
35. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024. [Math-shepherd: Verify and reinforce llms step-by-step without human annotations](https://md.research.elamur.ai/free/en/papers/wang-2024-math-shepherd-verify-reinforce-llms/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper…
36. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 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/). Advances in neural information processing systems, 35:24824– 24837.
37. Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, and Xing Chen. 2025. Graph-reward-SQL: Execution-free reinforcement learning for text-to-SQL via graph matching and stepwise reward. In Findings of the Asso… [find](https://scholar.google.com/scholar?q=Han+Weng%2C+Puzhen+Wu%2C+Cui+Longjie%2C+Yi+Zhan%2C+Boyi+Liu%2C+Yuanfeng+Song%2C+Dun+Zeng%2C+Yingxiang+Yang%2C+Qianru+Zhang%2C+Dong+Huang%2C+Xiaoming+Yin%2C+Yang+Sun%2C+and+Xing+Chen%2E+2025%2E+Graph%2Dreward%2DSQL%3A+Execution%2Dfree+re)
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, pages 25497–2… [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. Saisai Yang, Qingyi Huang, Jing Yuan, Liangyu Zha, Kai Tang, Yuhang Yang, Ning Wang, Yucheng Wei, Liyao Li, Wentao Ye, and 1 others. 2025. Tablegpt-r1: Advancing tabular reasoning through reinforcement learning. arXiv preprint arXiv:2512.20312. — [arXiv:2512.20312](https://arxiv.org/abs/2512.20312) [find](https://scholar.google.com/scholar?q=Saisai+Yang%2C+Qingyi+Huang%2C+Jing+Yuan%2C+Liangyu+Zha%2C+Kai+Tang%2C+Yuhang+Yang%2C+Ning+Wang%2C+Yucheng+Wei%2C+Liyao+Li%2C+Wentao+Ye%2C+and+1+others%2E+2025%2E+Tablegpt%2Dr1%3A+Advancing+tabular+reasoning+through+reinforcemen)
40. Zhewei Yao, Guoheng Sun, Lukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, and Yuxiong He. 2025. [Arctic-text2sql-r1: Simple rewards, strong reasoning in text-to-sql](https://md.research.elamur.ai/free/en/papers/yao-2026-arctic-text2sql-r1-simple-rewards/). arXiv preprint arXiv:2505.20315.
41. 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 2018 Conference on Empir…
42. Chao Zhang, Yuren Mao, Yijiang Fan, Yu Mi, Yunjun Gao, Lu Chen, Dongfang Lou, and Jinshu Lin. 2024a. Finsql: Model-agnostic llms-based text-to-sql framework for financial analysis. In Companion of the 2024 International Conference on Management of Data, pages 93–105. [find](https://scholar.google.com/scholar?q=Chao+Zhang%2C+Yuren+Mao%2C+Yijiang+Fan%2C+Yu+Mi%2C+Yunjun+Gao%2C+Lu+Chen%2C+Dongfang+Lou%2C+and+Jinshu+Lin%2E+2024a%2E+Finsql%3A+Model%2Dagnostic+llms%2Dbased+text%2Dto%2Dsql+framework+for+financial+analysis%2E+In+Companion+of+the)
43. Meng Zhang, Kexin Ma, Liyang Xu, Kedi Zhang, Yuanxi Peng, and Ruochun Jin. 2025a. Clear: A parser-independent disambiguation framework for nl2sql. In 2025 IEEE 41st International Conference on Data Engineering (ICDE), pages 1–14. IEEE. [find](https://scholar.google.com/scholar?q=Meng+Zhang%2C+Kexin+Ma%2C+Liyang+Xu%2C+Kedi+Zhang%2C+Yuanxi+Peng%2C+and+Ruochun+Jin%2E+2025a%2E+Clear%3A+A+parser%2Dindependent+disambiguation+framework+for+nl2sql%2E+In+2025+IEEE+41st+International+Conference+on+Data+En)
44. Tianshu Zhang, Xiang Yue, Yifei Li, and Huan Sun. 2024b. [Tablellama: Towards open large generalist models for tables](https://md.research.elamur.ai/free/en/papers/zhang-2023-tablellama-towards-open-large-generalist/). 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 6024–…
45. Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, and 1 others. 2025b. Tablellm: Enabling tabular data manipulation by llms in real office usage scenarios. In Findings of the Association for Computational Linguistics: ACL 2025, pa… [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+2025b%2E+Tablellm%3A+Enabling+tabular+data+manipulation+by+llms+in+rea)
46. Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Jian Tan, and Guoliang Li. 2025c. Reward-sql: Boosting text-to-sql via stepwise reasoning and process-supervised rewards. arXiv preprint arXiv:2505.04671. — [arXiv:2505.04671](https://arxiv.org/abs/2505.04671) [find](https://scholar.google.com/scholar?q=Yuxin+Zhang%2C+Meihao+Fan%2C+Ju+Fan%2C+Mingyang+Yi%2C+Yuyu+Luo%2C+Jian+Tan%2C+and+Guoliang+Li%2E+2025c%2E+Reward%2Dsql%3A+Boosting+text%2Dto%2Dsql+via+stepwise+reasoning+and+process%2Dsupervised+rewards%2E+arXiv+preprint+arXiv%3A2)
47. Danna Zheng, Mirella Lapata, and Jeff Pan. 2024. Archer: A human-labeled text-to-sql dataset with arithmetic, commonsense and hypothetical reasoning. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 94–111. [find](https://scholar.google.com/scholar?q=Danna+Zheng%2C+Mirella+Lapata%2C+and+Jeff+Pan%2E+2024%2E+Archer%3A+A+human%2Dlabeled+text%2Dto%2Dsql+dataset+with+arithmetic%2C+commonsense+and+hypothetical+reasoning%2E+In+Proceedings+of+the+18th+Conference+of+the+Europ)
48. 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 2 November 2026*