---
title: "Adaptive Text2GQL — paper by Niu et al. (2026)"
description: "The authors propose Adaptive Text2GQL, a training-free framework with three modules: Structural Twig Linking maps filtered… 38 references."
authors: ["Fang Niu", "Chaokun Wang", "Hang Zhang", "Songyao Wang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.804/"
doi: "10.18653/v1/2026.acl-long.804"
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/niu-2026-adaptive-text2gql-integrating-structural-twig/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/niu-2026-adaptive-text2gql-integrating-structural-twig/)

[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/21/) / Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning

# Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning

**Authors:** Fang Niu, Chaokun Wang, [Hang Zhang](https://md.research.elamur.ai/free/en/authors/hang-zhang/) and Songyao Wang · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.804/) · [PDF](https://aclanthology.org/2026.acl-long.804.pdf) · [DOI 10.18653/v1/2026.acl-long.804](https://doi.org/10.18653/v1/2026.acl-long.804) · [OpenAlex](https://openalex.org/W7166862919)

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

## Summary
Turning natural-language questions into graph database queries (Text2GQL) is harder than Text-to-SQL. Graph schemas are densely connected, and target languages differ widely: Cypher and SPARQL use declarative pattern matching, while Gremlin uses procedural traversal. Parallel training data is also scarce, so LLMs often produce queries that capture the user's intent but are structurally or syntactically invalid.

The authors propose Adaptive Text2GQL, a training-free framework with three modules:
- **Structural Twig Linking** maps filtered question tokens to schema elements using embedding similarity. It then assembles them into small, valid schema substructures ("twigs") through language-specific templates.
- **Evolutionary In-Context Learning** starts with no examples. It gradually builds a pool of execution-verified question–query pairs and retrieves similar ones as demonstrations.
- **Adversarial Execution-Guided Correction** is an agent that pairs a static critic with runtime verification against the database to repair faulty queries.

Experiments across Cypher, Gremlin and SPARQL show higher accuracy and executability than baselines, including on hard queries and very large schemas. This makes the framework relevant for unified natural-language access to fragmented graph database ecosystems.

## Key points
- At the custom dataset's hardest query level, the framework still attains 86.80% GAM, whereas standard baselines score 0% EX on the hard dataset.
- For schemas longer than 10,000 characters, it avoids "lost-in-the-middle" degradation, reaching a GAM of 81.23% and a peak EM of 70.11%.
- Average latency rises from about 3.80s (Naive baseline) to about 8.58s, a 2.3× increase. The average prompt is only 325.6 tokens, and the correction module activates in 15.2% of cases.
- A key limitation is that query verification depends on a live database connection, and performance drops in pure-generation settings without one.
- Code: github.com/nf202/Text2Graph.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 333 works · 87,019 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Fang Niu, Chaokun Wang, Hang Zhang and Songyao Wang. 2026. Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{niu2026adaptive,
  title = {{Adaptive Text2GQL: Integrating Structural Twig Linking and Evolutionary In-Context Learning}},
  author = {Fang Niu, Chaokun Wang, Hang Zhang and Songyao Wang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.804},
  url = {https://doi.org/10.18653/v1/2026.acl-long.804}
}
```

- [← previous Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search](https://md.research.elamur.ai/free/en/papers/ryu-2026-adaptive-planning-multi-attribute-controllable/)
- [next → Addressing Domain Shift in Health Coaching Note Analysis through Factorized Synthetic Data Generation](https://md.research.elamur.ai/free/en/papers/tanzer-2026-addressing-domain-shift-health-coaching/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/21/)

## References

38 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Caio Viktor S Avila, Vânia MP Vidal, Wellington Franco, and Marco A Casanova. 2024. Experiments with text-to-sparql based on chatgpt. In 2024 IEEE 18th international conference on semantic computing (ICSC), pages 277–284. IEEE. [find](https://scholar.google.com/scholar?q=Caio+Viktor+S+Avila%2C+V%C3%A2nia+MP+Vidal%2C+Wellington+Franco%2C+and+Marco+A+Casanova%2E+2024%2E+Experiments+with+text%2Dto%2Dsparql+based+on+chatgpt%2E+In+2024+IEEE+18th+international+conference+on+semantic+computing+%28)
2. Mehdi Ben Amor, Alexis Strappazzon, Michael Granitzer, Elöd Egyed-Zsigmond, and Jelena Mitrović. 2025. Instruct-to-sparql: A text-to-sparql dataset for training sparql agents. In Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval, pages 390–395. [find](https://scholar.google.com/scholar?q=Mehdi+Ben+Amor%2C+Alexis+Strappazzon%2C+Michael+Granitzer%2C+El%C3%B6d+Egyed%2DZsigmond%2C+and+Jelena+Mitrovic%CC%81%2E+2025%2E+Instruct%2Dto%2Dsparql%3A+A+text%2Dto%2Dsparql+dataset+for+training+sparql+agents%2E+In+Proceedings+of+the+2)
3. Alin Deutsch, Nadime Francis, Alastair Green, Keith Hare, Bei Li, Leonid Libkin, Tobias Lindaaker, Victor Marsault, Wim Martens, Jan Michels, and 1 others. 2022. Graph pattern matching in gql and sql/pgq. In Proceedings of the 2022 International Conference on Management of Data, pages 2246–2258. [find](https://scholar.google.com/scholar?q=Alin+Deutsch%2C+Nadime+Francis%2C+Alastair+Green%2C+Keith+Hare%2C+Bei+Li%2C+Leonid+Libkin%2C+Tobias+Lindaaker%2C+Victor+Marsault%2C+Wim+Martens%2C+Jan+Michels%2C+and+1+others%2E+2022%2E+Graph+pattern+matching+in+gql+and+sql%2F)
4. Yuankai Fan, Tonghui Ren, Can Huang, Zhenying He, and X Sean Wang. 2025. Grounding natural language to sql translation with data-based self-explanations. In 2025 IEEE 41st International Conference on Data Engineering (ICDE), pages 29–42. IEEE. [find](https://scholar.google.com/scholar?q=Yuankai+Fan%2C+Tonghui+Ren%2C+Can+Huang%2C+Zhenying+He%2C+and+X+Sean+Wang%2E+2025%2E+Grounding+natural+language+to+sql+translation+with+data%2Dbased+self%2Dexplanations%2E+In+2025+IEEE+41st+International+Conference+on+)
5. Nadime Francis, Alastair Green, Paolo Guagliardo, Leonid Libkin, Tobias Lindaaker, Victor Marsault, Stefan Plantikow, Mats Rydberg, Petra Selmer, and Andrés Taylor. 2018. Cypher: An evolving query language for property graphs. In Proceedings of the 2018 international conference on management of data… [find](https://scholar.google.com/scholar?q=Nadime+Francis%2C+Alastair+Green%2C+Paolo+Guagliardo%2C+Leonid+Libkin%2C+Tobias+Lindaaker%2C+Victor+Marsault%2C+Stefan+Plantikow%2C+Mats+Rydberg%2C+Petra+Selmer%2C+and+Andr%C3%A9s+Taylor%2E+2018%2E+Cypher%3A+An+evolving+query+lan)
6. Balaji Ganesan, Sambit Ghosh, Nitin Gupta, Manish Kesarwani, Sameep Mehta, and Renuka Sindhgatta. 2024. Llm-powered graphql generator for data retrieval. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pages 8657–8660. [find](https://scholar.google.com/scholar?q=Balaji+Ganesan%2C+Sambit+Ghosh%2C+Nitin+Gupta%2C+Manish+Kesarwani%2C+Sameep+Mehta%2C+and+Renuka+Sindhgatta%2E+2024%2E+Llm%2Dpowered+graphql+generator+for+data+retrieval%2E+In+Proceedings+of+the+Thirty%2DThird+Internation)
7. Chunxi Guo, Zhiliang Tian, Jintao Tang, Pancheng Wang, Zhihua Wen, Kang Yang, and Ting Wang. 2023. Prompting gpt-3.5 for text-to-sql with de-semanticization and skeleton retrieval. In Pacific Rim International Conference on Artificial Intelligence, pages 262–274. Springer. [find](https://scholar.google.com/scholar?q=Chunxi+Guo%2C+Zhiliang+Tian%2C+Jintao+Tang%2C+Pancheng+Wang%2C+Zhihua+Wen%2C+Kang+Yang%2C+and+Ting+Wang%2E+2023%2E+Prompting+gpt%2D3%2E5+for+text%2Dto%2Dsql+with+de%2Dsemanticization+and+skeleton+retrieval%2E+In+Pacific+Rim+Inte)
8. Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard De Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, and 1 others. 2021. [Knowledge graphs](https://md.research.elamur.ai/free/en/papers/hogan-2020-knowledge-graphs/). ACM Computing Surveys (Csur), 54(4):1–37.
9. Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, and Xiao Huang. 2025. Next-generation database interfaces: A survey of llm-based text-to-sql. IEEE Transactions on Knowledge and Data Engineering. [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+2025%2E+Next%2Dgeneration+database+interfaces%3A+A+survey+of+llm%2Dbased+text%2Dto%2Dsql%2E+IEEE+Transactions+on+Knowledg)
10. Wonseok Hwang, Jinyeong Yim, Seunghyun Park, and Minjoon Seo. 2019. A comprehensive exploration on wikisql with table-aware word contextualization. arXiv preprint arXiv:1902.01069. [find](https://scholar.google.com/scholar?q=Wonseok+Hwang%2C+Jinyeong+Yim%2C+Seunghyun+Park%2C+and+Minjoon+Seo%2E+2019%2E+A+comprehensive+exploration+on+wikisql+with+table%2Daware+word+contextualization%2E+arXiv+preprint+arXiv%3A1902%2E01069%2E)
11. ISO/IEC JTC 1/SC 32. 2024. ISO/IEC 39075:2024 – Information Technology – Database Languages – GQL. Technical report, International Organization for Standardization (ISO). [find](https://scholar.google.com/scholar?q=ISO%2FIEC+JTC+1%2FSC+32%2E+2024%2E+ISO%2FIEC+39075%3A2024+%E2%80%93+Information+Technology+%E2%80%93+Database+Languages+%E2%80%93+GQL%2E+Technical+report%2C+International+Organization+for+Standardization+%28ISO%29%2E)
12. Ali Buğra Kanburoğlu and Faik Boray Tek. 2024. Text-to-sql: A methodical review of challenges and models. Turkish Journal of Electrical Engineering and Computer Sciences, 32(3):403–419. [find](https://scholar.google.com/scholar?q=Ali+Bug%CC%86ra+Kanburog%CC%86lu+and+Faik+Boray+Tek%2E+2024%2E+Text%2Dto%2Dsql%3A+A+methodical+review+of+challenges+and+models%2E+Turkish+Journal+of+Electrical+Engineering+and+Computer+Sciences%2C+32%283%29%3A403%E2%80%93419%2E)
13. Lyndon S Kennedy, Apostol Natsev, and Shih-Fu Chang. 2005. Automatic discovery of query-class-dependent models for multimodal search. In Proceedings of the 13th annual ACM international conference on multimedia, pages 882–891. [find](https://scholar.google.com/scholar?q=Lyndon+S+Kennedy%2C+Apostol+Natsev%2C+and+Shih%2DFu+Chang%2E+2005%2E+Automatic+discovery+of+query%2Dclass%2Ddependent+models+for+multimodal+search%2E+In+Proceedings+of+the+13th+annual+ACM+international+conference+on+)
14. Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, and 1 others. 2024. Spider 2.0: Evaluating language models on real-world enterprise text-to-sql workflows. arXiv preprint arXiv:2411.07763. — [arXiv:2411.07763](https://arxiv.org/abs/2411.07763) [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+and+1+others%2E+2024%2E+Spider+2%2E0%3A+Evaluating+language+models+on+real%2D)
15. 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. Proceedings of the ACM on Management of Data, 2(3):1–28. [find](https://scholar.google.com/scholar?q=Haoyang+Li%2C+Jing+Zhang%2C+Hanbing+Liu%2C+Ju+Fan%2C+Xiaokang+Zhang%2C+Jun+Zhu%2C+Renjie+Wei%2C+Hongyan+Pan%2C+Cuiping+Li%2C+and+Hong+Chen%2E+2024a%2E+Codes%3A+Towards+building+open%2Dsource+language+models+for+text%2Dto%2Dsql%2E+Pr)
16. Zhaodonghui Li, Haitao Yuan, Huiming Wang, Gao Cong, and Lidong Bing. 2024b. Llm-r2: A large language model enhanced rule-based rewrite system for boosting query efficiency. Proceedings of the VLDB Endowment, 18(1):53–65. [find](https://scholar.google.com/scholar?q=Zhaodonghui+Li%2C+Haitao+Yuan%2C+Huiming+Wang%2C+Gao+Cong%2C+and+Lidong+Bing%2E+2024b%2E+Llm%2Dr2%3A+A+large+language+model+enhanced+rule%2Dbased+rewrite+system+for+boosting+query+efficiency%2E+Proceedings+of+the+VLDB+En)
17. Zhenwen Li and Tao Xie. 2024. Using llm to select the right sql query from candidates. CoRR. [find](https://scholar.google.com/scholar?q=Zhenwen+Li+and+Tao+Xie%2E+2024%2E+Using+llm+to+select+the+right+sql+query+from+candidates%2E+CoRR%2E)
18. Yuanyuan Liang, Lei Pan, Tingyu Xie, Yunshi Lan, and Weining Qian. 2025. Multi-turn natural language to graph query language translation. arXiv preprint arXiv:2508.01871. — [arXiv:2508.01871](https://arxiv.org/abs/2508.01871) [find](https://scholar.google.com/scholar?q=Yuanyuan+Liang%2C+Lei+Pan%2C+Tingyu+Xie%2C+Yunshi+Lan%2C+and+Weining+Qian%2E+2025%2E+Multi%2Dturn+natural+language+to+graph+query+language+translation%2E+arXiv+preprint+arXiv%3A2508%2E01871%2E+%E2%80%94+%5BarXiv%3A2508%2E01871%5D%28https%3A%2F%2F)
19. Yuanyuan Liang, Keren Tan, Tingyu Xie, Wenbiao Tao, Siyuan Wang, Yunshi Lan, and Weining Qian. 2024a. Aligning large language models to a domain-specific graph database for nl2gql. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 1367–1377. [find](https://scholar.google.com/scholar?q=Yuanyuan+Liang%2C+Keren+Tan%2C+Tingyu+Xie%2C+Wenbiao+Tao%2C+Siyuan+Wang%2C+Yunshi+Lan%2C+and+Weining+Qian%2E+2024a%2E+Aligning+large+language+models+to+a+domain%2Dspecific+graph+database+for+nl2gql%2E+In+Proceedings+of+t)
20. Yuanyuan Liang, Tingyu Xie, Gan Peng, Zihao Huang, Yunshi Lan, and Weining Qian. 2024b. Nat-nl2gql: A novel multi-agent framework for translating natural language to graph query language. CoRR. [find](https://scholar.google.com/scholar?q=Yuanyuan+Liang%2C+Tingyu+Xie%2C+Gan+Peng%2C+Zihao+Huang%2C+Yunshi+Lan%2C+and+Weining+Qian%2E+2024b%2E+Nat%2Dnl2gql%3A+A+novel+multi%2Dagent+framework+for+translating+natural+language+to+graph+query+language%2E+CoRR%2E)
21. Yang Liu, Xin Wang, Jiake Ge, Hui Wang, Dawei Xu, and Yongzhe Jia. 2024. Text to graph query using filter condition attributes. Proceedings of the VLDB Endowment. ISSN, 2150:8097. [find](https://scholar.google.com/scholar?q=Yang+Liu%2C+Xin+Wang%2C+Jiake+Ge%2C+Hui+Wang%2C+Dawei+Xu%2C+and+Yongzhe+Jia%2E+2024%2E+Text+to+graph+query+using+filter+condition+attributes%2E+Proceedings+of+the+VLDB+Endowment%2E+ISSN%2C+2150%3A8097%2E)
22. Neo4j-Text2Cypher. 2024. [https://huggingface.co/datasets/neo4j/text2cypher-2024v1](https://huggingface.co/datasets/neo4j/text2cypher-2024v1). (last updated on 2025-03). [↗](https://huggingface.co/datasets/neo4j/text2cypher-2024v1)
23. Makbule Gulcin Ozsoy, Leila Messallem, Jon Besga, and Gianandrea Minneci. 2025. Text2cypher: Bridging natural language and graph databases. In Proceedings of the Workshop on Generative AI and Knowledge Graphs (GenAIK), pages 100–108. [find](https://scholar.google.com/scholar?q=Makbule+Gulcin+Ozsoy%2C+Leila+Messallem%2C+Jon+Besga%2C+and+Gianandrea+Minneci%2E+2025%2E+Text2cypher%3A+Bridging+natural+language+and+graph+databases%2E+In+Proceedings+of+the+Workshop+on+Generative+AI+and+Knowledg)
24. Jorge Pérez, Marcelo Arenas, and Claudio Gutierrez. 2009. Semantics and complexity of sparql. ACM Transactions on Database Systems (TODS), 34(3):1– 45. [find](https://scholar.google.com/scholar?q=Jorge+P%C3%A9rez%2C+Marcelo+Arenas%2C+and+Claudio+Gutierrez%2E+2009%2E+Semantics+and+complexity+of+sparql%2E+ACM+Transactions+on+Database+Systems+%28TODS%29%2C+34%283%29%3A1%E2%80%93+45%2E)
25. Antonio Quiña-Mera, Pablo Fernandez, José María García, and Antonio Ruiz-Cortés. 2023. Graphql: A systematic mapping study. ACM computing surveys, 55(10):1–35. [find](https://scholar.google.com/scholar?q=Antonio+Qui%C3%B1a%2DMera%2C+Pablo+Fernandez%2C+Jos%C3%A9+Mar%C3%ADa+Garc%C3%ADa%2C+and+Antonio+Ruiz%2DCort%C3%A9s%2E+2023%2E+Graphql%3A+A+systematic+mapping+study%2E+ACM+computing+surveys%2C+55%2810%29%3A1%E2%80%9335%2E)
26. Marko A Rodriguez. 2015. The gremlin graph traversal machine and language (invited talk). In Proceedings of the 15th symposium on database programming languages, pages 1–10. [find](https://scholar.google.com/scholar?q=Marko+A+Rodriguez%2E+2015%2E+The+gremlin+graph+traversal+machine+and+language+%28invited+talk%29%2E+In+Proceedings+of+the+15th+symposium+on+database+programming+languages%2C+pages+1%E2%80%9310%2E)
27. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, and 1 others. 2023. [Code llama: Open foundation models for code](https://md.research.elamur.ai/free/en/papers/roziere-2024-code-llama-open-foundation-models/). arXiv preprint arXiv:2308.12950.
28. Shashank Sheshar Singh, Samya Muhuri, Shivansh Mishra, Divya Srivastava, Harish Kumar Shakya, and Neeraj Kumar. 2024. Social network analysis: A survey on process, tools, and application. ACM computing surveys, 56(8):1–39. [find](https://scholar.google.com/scholar?q=Shashank+Sheshar+Singh%2C+Samya+Muhuri%2C+Shivansh+Mishra%2C+Divya+Srivastava%2C+Harish+Kumar+Shakya%2C+and+Neeraj+Kumar%2E+2024%2E+Social+network+analysis%3A+A+survey+on+process%2C+tools%2C+and+application%2E+ACM+computin)
29. Aman Tiwari, Shiva Krishna Reddy Malay, Vikas Yadav, Masoud Hashemi, and Sathwik Tejaswi Madhusudhan. 2025. Auto-cypher: Improving llms on cypher generation via llm-supervised generation-verification framework. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Assoc… [find](https://scholar.google.com/scholar?q=Aman+Tiwari%2C+Shiva+Krishna+Reddy+Malay%2C+Vikas+Yadav%2C+Masoud+Hashemi%2C+and+Sathwik+Tejaswi+Madhusudhan%2E+2025%2E+Auto%2Dcypher%3A+Improving+llms+on+cypher+generation+via+llm%2Dsupervised+generation%2Dverification+)
30. 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.
31. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2024. [C-pack: Packed resources for general chinese embeddings](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/). In Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval, pages 641–649.
32. 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/). arXiv preprint arXiv:1809.08887.
33. Hanchong Zhang, Ruisheng Cao, Lu Chen, Hongshen Xu, and Kai Yu. 2023. Act-sql: In-context learning for text-to-sql with automatically-generated chain-of-thought. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3501–3532. [find](https://scholar.google.com/scholar?q=Hanchong+Zhang%2C+Ruisheng+Cao%2C+Lu+Chen%2C+Hongshen+Xu%2C+and+Kai+Yu%2E+2023%2E+Act%2Dsql%3A+In%2Dcontext+learning+for+text%2Dto%2Dsql+with+automatically%2Dgenerated+chain%2Dof%2Dthought%2E+In+Findings+of+the+Association+for+Com)
34. Hang Zhang, Chaokun Wang, Hongwei Li, Cheng Wu, Songyao Wang, Yabin Liu, Gengyuan Shi, and Ziyang Liu. 2025. Plforge: Enhancing language models for natural language to procedural extensions of sql. Proceedings of the ACM on Management of Data, 3(6):1–28. [find](https://scholar.google.com/scholar?q=Hang+Zhang%2C+Chaokun+Wang%2C+Hongwei+Li%2C+Cheng+Wu%2C+Songyao+Wang%2C+Yabin+Liu%2C+Gengyuan+Shi%2C+and+Ziyang+Liu%2E+2025%2E+Plforge%3A+Enhancing+language+models+for+natural+language+to+procedural+extensions+of+sql%2E+Pr)
35. Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, and Hongwei Li. 2025a. Lagcl4rec: When llms activate interactions potential in graph contrastive learning for recommendation. In Findings of the Association for Computational Linguistics: EMNLP 2025,… [find](https://scholar.google.com/scholar?q=Leqi+Zheng%2C+Chaokun+Wang%2C+Canzhi+Chen%2C+Jiajun+Zhang%2C+Cheng+Wu%2C+Zixin+Song%2C+Shannan+Yan%2C+Ziyang+Liu%2C+and+Hongwei+Li%2E+2025a%2E+Lagcl4rec%3A+When+llms+activate+interactions+potential+in+graph+contrastive+lea)
36. Leqi Zheng, Chaokun Wang, Zixin Song, Cheng Wu, Shannan Yan, Jiajun Zhang, and Ziyang Liu. 2025b. Negative feedback really matters: Signed dual-channel graph contrastive learning framework for recommendation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Leqi+Zheng%2C+Chaokun+Wang%2C+Zixin+Song%2C+Cheng+Wu%2C+Shannan+Yan%2C+Jiajun+Zhang%2C+and+Ziyang+Liu%2E+2025b%2E+Negative+feedback+really+matters%3A+Signed+dual%2Dchannel+graph+contrastive+learning+framework+for+recomme)
37. Leqi Zheng, Jiajun Zhang, Canzhi Chen, Chaokun Wang, Hongwei Li, Yuying Li, Yaoxin Mao, Shannan Yan, Zixin Song, Zhiyuan Feng, Zhaolu Kang, Zirong Chen, Hang Zhang, Qiang Liu, Liang Wang, and Ziyang Liu. 2026. What should i cite? a rag benchmark for academic citation prediction. In Proceedings of th… [find](https://scholar.google.com/scholar?q=Leqi+Zheng%2C+Jiajun+Zhang%2C+Canzhi+Chen%2C+Chaokun+Wang%2C+Hongwei+Li%2C+Yuying+Li%2C+Yaoxin+Mao%2C+Shannan+Yan%2C+Zixin+Song%2C+Zhiyuan+Feng%2C+Zhaolu+Kang%2C+Zirong+Chen%2C+Hang+Zhang%2C+Qiang+Liu%2C+Liang+Wang%2C+and+Ziyang+L)
38. Yuhang Zhou, Yu He, Siyu Tian, Yuchen Ni, Zhangyue Yin, Xiang Liu, Chuanjun Ji, Sen Liu, Xipeng Qiu, Guangnan Ye, and 1 others. 2024. r3-nl2gql: A model coordination and knowledge graph alignment approach for nl2gql. In Findings of the association for computational linguistics: EMNLP 2024, pages 136… [find](https://scholar.google.com/scholar?q=Yuhang+Zhou%2C+Yu+He%2C+Siyu+Tian%2C+Yuchen+Ni%2C+Zhangyue+Yin%2C+Xiang+Liu%2C+Chuanjun+Ji%2C+Sen+Liu%2C+Xipeng+Qiu%2C+Guangnan+Ye%2C+and+1+others%2E+2024%2E+r3%2Dnl2gql%3A+A+model+coordination+and+knowledge+graph+alignment+appr)

*Updated 1 November 2026*