---
title: "SchemaGraphSQL — paper by Safdarian et al. (2026)"
description: "Enterprise databases can contain hundreds of tables, so passing the whole schema to an LLM-based Text-to-SQL system… 29 references."
authors: ["AmirHossein Safdarian", "Milad Mohammadi", "Ehsan Jahanbakhsh Bashirloo", "Mona Shahamat Naderi", "Heshaam Faili"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.134/"
doi: "10.18653/v1/2026.findings-eacl.134"
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/safdarian-2026-schemagraphsql-efficient-schema-linking-pathfinding/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/safdarian-2026-schemagraphsql-efficient-schema-linking-pathfinding/)

[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/42/) / SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases

# SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases

**Authors:** AmirHossein Safdarian, Milad Mohammadi, Ehsan Jahanbakhsh Bashirloo, Mona Shahamat Naderi and Heshaam Faili · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 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-eacl.134/) · [PDF](https://aclanthology.org/2026.findings-eacl.134.pdf) · [DOI 10.18653/v1/2026.findings-eacl.134](https://doi.org/10.18653/v1/2026.findings-eacl.134) · [OpenAlex](https://openalex.org/W6979335988)

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

## Summary
Enterprise databases can contain hundreds of tables, so passing the whole schema to an LLM-based Text-to-SQL system wastes tokens and adds noise. Schema linking addresses this by selecting only the relevant tables. Existing linkers, however, often need supervised training, multi-step pipelines or fragile prompts. SchemaGraphSQL treats schema linking as a graph search problem and needs no training. Tables become nodes and foreign keys become edges. When keys are absent or unreliable, an LLM first proposes joinable table pairs. A single call to a lightweight LLM then names the source table (where filters apply) and the destination table (which holds the requested outputs). A Dijkstra-style shortest-path search connects them, and the tables on that path form a compact, connected sub-schema for the SQL generator. The main configuration, force-union, favours recall: it takes the union of paths over several sources and destinations. The authors report state-of-the-art recall-oriented linking on BIRD and Spider 2.0 Lite and higher end-to-end execution accuracy across model families. Inference cost stays very low, which makes the approach practical for production systems.

## Key points
- On average, each query consumes about 4.6K tokens of input and generates 14 tokens of output. A second small LLM call, used only to break ties between equally short paths, was needed in just 1.7% of BIRD-Dev examples.
- Evaluation covers BIRD Dev (1,534 questions, 11 databases, clean FK annotations) and Spider 2.0 Lite (547 test examples, 158 databases, with missing or incomplete foreign keys).
- Source/destination extraction uses Gemini 2.5 Flash. The method is compared with prompt-based linkers (DIN-SQL, PET-SQL, MAC-SQL, MCS-SQL, RSL-SQL, LinkAlign), with retrieval using multilingual-E5-large-instruct, and with fine-tuned systems (DTS-SQL, ExSL).
- Configurations: force-union gives the best recall and execution accuracy, 1–1 gives the most compact context, and n–n gives the best F1/EMR on BIRD-Dev. Recall-oriented linking correlated most strongly with execution accuracy.
- Stated limitations: weak handling of deeply nested queries, lower precision on dense or noisy FK graphs, unweighted join paths, and testing only via hosted APIs (Gemma, Gemini, GPT-5).

*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

- [University of Tehran](https://md.research.elamur.ai/free/en/universities/university-of-tehran/) — University, Tehran, Iran · 8 works · 182 citations
- [Sharif University of Technology](https://md.research.elamur.ai/free/en/universities/sharif-university-of-technology/) — University, Tehran, Iran · 5 works · 524 citations

📚 Shelves (5): [🖥️ 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 Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 64 works

🧭 Topics (2): [🧾 Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) · 185 works · [💻 Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · 129 works

## Cite

Cite as: AmirHossein Safdarian, Milad Mohammadi, Ehsan Jahanbakhsh Bashirloo, Mona Shahamat Naderi and Heshaam Faili. 2026. SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{safdarian2026schemagraphsql,
  title = {{SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases}},
  author = {AmirHossein Safdarian, Milad Mohammadi, Ehsan Jahanbakhsh Bashirloo, Mona Shahamat Naderi and Heshaam Faili},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.134},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.134}
}
```

- [← previous SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes](https://md.research.elamur.ai/free/en/papers/wang-2026-scenealign-aligning-multimodal-reasoning-scene/)
- [next → Schützen: Evaluating LLM Safety in Bulgarian and German Contexts](https://md.research.elamur.ai/free/en/papers/georgiev-2026-sch-utzen-evaluating-llm-safety/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/)

## References

29 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adrián Bazaga, Pietro Liò, and Gos Micklem. 2024. Sqlformer: Deep auto-regressive query graph generation for text-to-sql translation. Preprint, arXiv:2310.18376. — [arXiv:2310.18376](https://arxiv.org/abs/2310.18376) [find](https://scholar.google.com/scholar?q=Adri%C3%A1n+Bazaga%2C+Pietro+Li%C3%B2%2C+and+Gos+Micklem%2E+2024%2E+Sqlformer%3A+Deep+auto%2Dregressive+query+graph+generation+for+text%2Dto%2Dsql+translation%2E+Preprint%2C+arXiv%3A2310%2E18376%2E+%E2%80%94+%5BarXiv%3A2310%2E18376%5D%28https%3A%2F%2Farxiv%2Eorg)
2. Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, and Kai Yu. 2021. [LGESQL: Line graph enhanced text-to-SQL model with mixed local and non-local relations](https://md.research.elamur.ai/free/en/papers/cao-2021-lgesql-line-graph-enhanced-text/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Na…
3. Zhenbiao Cao, Yuanlei Zheng, Zhihao Fan, Xiaojin Zhang, Wei Chen, and Xiang Bai. 2024. Rsl-sql: Robust schema linking in text-to-sql generation. Preprint, arXiv:2411.00073. — [arXiv:2411.00073](https://arxiv.org/abs/2411.00073) [find](https://scholar.google.com/scholar?q=Zhenbiao+Cao%2C+Yuanlei+Zheng%2C+Zhihao+Fan%2C+Xiaojin+Zhang%2C+Wei+Chen%2C+and+Xiang+Bai%2E+2024%2E+Rsl%2Dsql%3A+Robust+schema+linking+in+text%2Dto%2Dsql+generation%2E+Preprint%2C+arXiv%3A2411%2E00073%2E+%E2%80%94+%5BarXiv%3A2411%2E00073%5D%28https%3A)
4. Zhi Chen, Lu Chen, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu, and Kai Yu. 2021. ShadowGNN: Graph projection neural network for text-to-SQL parser. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, page… [find](https://scholar.google.com/scholar?q=Zhi+Chen%2C+Lu+Chen%2C+Yanbin+Zhao%2C+Ruisheng+Cao%2C+Zihan+Xu%2C+Su+Zhu%2C+and+Kai+Yu%2E+2021%2E+ShadowGNN%3A+Graph+projection+neural+network+for+text%2Dto%2DSQL+parser%2E+In+Proceedings+of+the+2021+Conference+of+the+North+)
5. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, and 3290 [other…](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/)
6. Yujian Gan, Xinyun Chen, and Matthew Purver. 2023. Re-appraising the schema linking for text-to-SQL. In Findings of the Association for Computational Linguistics: ACL 2023, pages 835–852, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yujian+Gan%2C+Xinyun+Chen%2C+and+Matthew+Purver%2E+2023%2E+Re%2Dappraising+the+schema+linking+for+text%2Dto%2DSQL%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2023%2C+pages+835%E2%80%93852%2C+Toronto%2C+Can)
7. Michael Glass, Mustafa Eyceoz, Dharmashankar Subramanian, Gaetano Rossiello, Long Vu, and Alfio Gliozzo. 2025. Extractive schema linking for text-to-sql. Preprint, arXiv:2501.17174. — [arXiv:2501.17174](https://arxiv.org/abs/2501.17174) [find](https://scholar.google.com/scholar?q=Michael+Glass%2C+Mustafa+Eyceoz%2C+Dharmashankar+Subramanian%2C+Gaetano+Rossiello%2C+Long+Vu%2C+and+Alfio+Gliozzo%2E+2025%2E+Extractive+schema+linking+for+text%2Dto%2Dsql%2E+Preprint%2C+arXiv%3A2501%2E17174%2E+%E2%80%94+%5BarXiv%3A2501%2E1717)
8. Zheng Gong and Ying Sun. 2024. Graph reasoning enhanced language models for text-to-sql. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 2447–2451, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Zheng+Gong+and+Ying+Sun%2E+2024%2E+Graph+reasoning+enhanced+language+models+for+text%2Dto%2Dsql%2E+In+Proceedings+of+the+47th+International+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+Retrie)
9. Dongjun Lee, Choongwon Park, Jaehyuk Kim, and Heesoo Park. 2025. [MCS-SQL: Leveraging multiple prompts and multiple-choice selection for text-to-SQL generation](https://md.research.elamur.ai/free/en/papers/lee-2025-mcs-sql-leveraging-multiple-prompts/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 337–353, Abu Dhabi, UAE. Association for Computation…
10. Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin SU, ZHAOQING SUO, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, and Tao Yu. 2025. Spider 2.0: Evaluating language models on real-world enterprise text-to-SQL workflows. I… [find](https://scholar.google.com/scholar?q=Fangyu+Lei%2C+Jixuan+Chen%2C+Yuxiao+Ye%2C+Ruisheng+Cao%2C+Dongchan+Shin%2C+Hongjin+SU%2C+ZHAOQING+SUO%2C+Hongcheng+Gao%2C+Wenjing+Hu%2C+Pengcheng+Yin%2C+Victor+Zhong%2C+Caiming+Xiong%2C+Ruoxi+Sun%2C+Qian+Liu%2C+Sida+Wang%2C+and+Ta)
11. Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, and Tat-Seng Chua. 2020. Re-examining the role of schema linking in text-to-SQL. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6943–6954, Online. Association for Computatio… [find](https://scholar.google.com/scholar?q=Wenqiang+Lei%2C+Weixin+Wang%2C+Zhixin+Ma%2C+Tian+Gan%2C+Wei+Lu%2C+Min%2DYen+Kan%2C+and+Tat%2DSeng+Chua%2E+2020%2E+Re%2Dexamining+the+role+of+schema+linking+in+text%2Dto%2DSQL%2E+In+Proceedings+of+the+2020+Conference+on+Empirical)
12. Haoyang Li, Jing Zhang, Cuiping Li, and Hong Chen. 2023a. [Resdsql: Decoupling schema linking and skeleton parsing for text-to-sql](https://md.research.elamur.ai/free/en/papers/li-2023-resdsql-decoupling-schema-linking-skeleton/). In AAAI Conference on Artificial Intelligence.
13. Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, and Yongbin Li. 2023b. Graphix-t5: Mixing pre-trained transformers with graph-aware layers for text-to-sql parsing. Preprint, arXiv:2301.07507. — [arXiv:2301.07507](https://arxiv.org/abs/2301.07507) [find](https://scholar.google.com/scholar?q=Jinyang+Li%2C+Binyuan+Hui%2C+Reynold+Cheng%2C+Bowen+Qin%2C+Chenhao+Ma%2C+Nan+Huo%2C+Fei+Huang%2C+Wenyu+Du%2C+Luo+Si%2C+and+Yongbin+Li%2E+2023b%2E+Graphix%2Dt5%3A+Mixing+pre%2Dtrained+transformers+with+graph%2Daware+layers+for+text)
14. Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, Xuanhe Zhou, Ma Chenhao, Guoliang Li, Kevin Chang, Fei Huang, Reynold Cheng, and Yongbin Li. 2023c. [Can llm already serve as a database interface?](https://md.research.elamur.ai/free/en/papers/li-2023-llm-already-serve-database-interface/) a big bench for large-scale database grou…
15. Zhishuai Li, Xiang Wang, Jingjing Zhao, Sun Yang, Guoqing Du, Xiaoru Hu, Bin Zhang, Yuxiao Ye, Ziyue Li, Rui Zhao, and Hangyu Mao. 2024. Pet-sql: A prompt-enhanced two-round refinement of text-to-sql with cross-consistency. Preprint, arXiv:2403.09732. — [arXiv:2403.09732](https://arxiv.org/abs/2403.09732) [find](https://scholar.google.com/scholar?q=Zhishuai+Li%2C+Xiang+Wang%2C+Jingjing+Zhao%2C+Sun+Yang%2C+Guoqing+Du%2C+Xiaoru+Hu%2C+Bin+Zhang%2C+Yuxiao+Ye%2C+Ziyue+Li%2C+Rui+Zhao%2C+and+Hangyu+Mao%2E+2024%2E+Pet%2Dsql%3A+A+prompt%2Denhanced+two%2Dround+refinement+of+text%2Dto%2Dsql+)
16. Geling Liu, Yunzhi Tan, Ruichao Zhong, Yuanzhen Xie, Lingchen Zhao, Qian Wang, Bo Hu, and Zang Li. 2025. Solid-SQL: Enhanced schema-linking based in-context learning for robust text-to-SQL. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9793–9803, Abu Dhabi,… [find](https://scholar.google.com/scholar?q=Geling+Liu%2C+Yunzhi+Tan%2C+Ruichao+Zhong%2C+Yuanzhen+Xie%2C+Lingchen+Zhao%2C+Qian+Wang%2C+Bo+Hu%2C+and+Zang+Li%2E+2025%2E+Solid%2DSQL%3A+Enhanced+schema%2Dlinking+based+in%2Dcontext+learning+for+robust+text%2Dto%2DSQL%2E+In+Proceed)
17. OpenAI. 2025. Gpt-5 system card. Technical report, OpenAI. Technical report. Describes GPT-5 model variants including gpt-5-mini and gpt-5-nano. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt%2D5+system+card%2E+Technical+report%2C+OpenAI%2E+Technical+report%2E+Describes+GPT%2D5+model+variants+including+gpt%2D5%2Dmini+and+gpt%2D5%2Dnano%2E)
18. Mohammadreza Pourreza and Davood Rafiei. 2023. [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/). Preprint, arXiv:2304.11015.
19. Mohammadreza Pourreza and Davood Rafiei. 2024. Dts-sql: Decomposed text-to-sql with small large language models. Preprint, arXiv:2402.01117. [find](https://scholar.google.com/scholar?q=Mohammadreza+Pourreza+and+Davood+Rafiei%2E+2024%2E+Dts%2Dsql%3A+Decomposed+text%2Dto%2Dsql+with+small+large+language+models%2E+Preprint%2C+arXiv%3A2402%2E01117%2E)
20. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, and Zhoujun Li. 2025a. [Mac-sql: A multi-agent collaborative framework for text-to-sql](https://md.research.elamur.ai/free/en/papers/wang-2025-mac-sql-multi-agent-collaborative/). Preprint, arXiv:2312.11242.
21. Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xianpei Han, Le Sun, Hao Wang, and Zhenyu Zeng. 2025b. Dbcopilot: Natural language querying over massive databases via schema routing. Preprint, arXiv:2312.03463. — [arXiv:2312.03463](https://arxiv.org/abs/2312.03463) [find](https://scholar.google.com/scholar?q=Tianshu+Wang%2C+Xiaoyang+Chen%2C+Hongyu+Lin%2C+Xianpei+Han%2C+Le+Sun%2C+Hao+Wang%2C+and+Zhenyu+Zeng%2E+2025b%2E+Dbcopilot%3A+Natural+language+querying+over+massive+databases+via+schema+routing%2E+Preprint%2C+arXiv%3A2312%2E034)
22. Xixi Wang, Miguel Costa, Jordanka Kovaceva, Shuai Wang, and Francisco C Pereira. 2025c. Plugging schema graph into multi-table qa: A human-guided framework for reducing llm reliance. arXiv preprint arXiv:2506.04427. [find](https://scholar.google.com/scholar?q=Xixi+Wang%2C+Miguel+Costa%2C+Jordanka+Kovaceva%2C+Shuai+Wang%2C+and+Francisco+C+Pereira%2E+2025c%2E+Plugging+schema+graph+into+multi%2Dtable+qa%3A+A+human%2Dguided+framework+for+reducing+llm+reliance%2E+arXiv+preprint+ar)
23. Yihan Wang, Peiyu Liu, and Xin Yang. 2025d. Linkalign: Scalable schema linking for real-world large-scale multi-database text-to-sql. Preprint, arXiv:2503.18596. [find](https://scholar.google.com/scholar?q=Yihan+Wang%2C+Peiyu+Liu%2C+and+Xin+Yang%2E+2025d%2E+Linkalign%3A+Scalable+schema+linking+for+real%2Dworld+large%2Dscale+multi%2Ddatabase+text%2Dto%2Dsql%2E+Preprint%2C+arXiv%3A2503%2E18596%2E)
24. Guanming Xiong, Junwei Bao, Hongfei Jiang, Yang Song, and Wen Zhao. 2024. Interactive-t2s: Multi-turn interactions for text-to-sql with large language models. Preprint, arXiv:2408.11062. — [arXiv:2408.11062](https://arxiv.org/abs/2408.11062) [find](https://scholar.google.com/scholar?q=Guanming+Xiong%2C+Junwei+Bao%2C+Hongfei+Jiang%2C+Yang+Song%2C+and+Wen+Zhao%2E+2024%2E+Interactive%2Dt2s%3A+Multi%2Dturn+interactions+for+text%2Dto%2Dsql+with+large+language+models%2E+Preprint%2C+arXiv%3A2408%2E11062%2E+%E2%80%94+%5BarXiv%3A2408)
25. Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, and Dragomir Radev. 2018. [TypeSQL: Knowledge-based type-aware neural text-to-SQL generation](https://md.research.elamur.ai/free/en/papers/yu-2018-typesql-knowledge-based-type-aware/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Pa…
26. Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, Sun Yang, Chi Harold Liu, Rui Zhao, Ziyue Li, and Hangyu Mao. 2024. Benchmarking the text-to-sql capability of large language models: A comprehensive evaluation. Preprint, arXiv:2403.02951. — [arXiv:2403.02951](https://arxiv.org/abs/2403.02951) [find](https://scholar.google.com/scholar?q=Bin+Zhang%2C+Yuxiao+Ye%2C+Guoqing+Du%2C+Xiaoru+Hu%2C+Zhishuai+Li%2C+Sun+Yang%2C+Chi+Harold+Liu%2C+Rui+Zhao%2C+Ziyue+Li%2C+and+Hangyu+Mao%2E+2024%2E+Benchmarking+the+text%2Dto%2Dsql+capability+of+large+language+models%3A+A+compre)
27. Xiaohu Zhu, Qian Li, Lizhen Cui, and Yongkang Liu. 2024. Large language model enhanced text-to-sql generation: A survey. Preprint, arXiv:2410.06011. — [arXiv:2410.06011](https://arxiv.org/abs/2410.06011) [find](https://scholar.google.com/scholar?q=Xiaohu+Zhu%2C+Qian+Li%2C+Lizhen+Cui%2C+and+Yongkang+Liu%2E+2024%2E+Large+language+model+enhanced+text%2Dto%2Dsql+generation%3A+A+survey%2E+Preprint%2C+arXiv%3A2410%2E06011%2E+%E2%80%94+%5BarXiv%3A2410%2E06011%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2410%2E060)
28. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+Louis+Rouillard%2C+Thomas+Mesnard%2C+Geoffrey)
29. Bailin Wang, Richard Shin, Xiaodong Liu, Oleksandr Polozov, and Matthew Richardson. 2020. [RAT-SQL: Relation-aware schema encoding and linking for text-to-SQL parsers](https://md.research.elamur.ai/free/en/papers/wang-2020-rat-sql-relation-aware-schema/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7567–7578, Online. Association for…

*Updated 1 November 2026*