---
title: "CypherSmith — paper by Zhang et al. (2026)"
description: "The authors introduce CypherSmith, an instruction-tuning resource generated entirely with open-source LLMs. 61 references."
authors: ["Zeyu Zhang", "Kexuan Sun", "Zheng Tang", "Jens-S. Vöckler", "Thien Huu Nguyen", "Thuy Vu"]
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.1601/"
doi: "10.18653/v1/2026.acl-long.1601"
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-cyphersmith-transforming-text-cypher-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-cyphersmith-transforming-text-cypher-generation/)

[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/) / CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data

# CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data

**Authors:** [Zeyu Zhang](https://md.research.elamur.ai/free/en/authors/zeyu-zhang/), Kexuan Sun, [Zheng Tang](https://md.research.elamur.ai/free/en/authors/zheng-tang/), Jens-S. Vöckler, [Thien Huu Nguyen](https://md.research.elamur.ai/free/en/authors/thien-huu-nguyen/) and Thuy Vu · **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.1601/) · [PDF](https://aclanthology.org/2026.acl-long.1601.pdf) · [DOI 10.18653/v1/2026.acl-long.1601](https://doi.org/10.18653/v1/2026.acl-long.1601) · [OpenAlex](https://openalex.org/W7166830819)

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

## Summary
Text-to-Cypher means turning natural-language questions into Cypher queries for property graphs such as Neo4j. It is increasingly relevant for knowledge-graph retrieval in industry, but it lags behind Text-to-SQL and Text-to-SPARQL. The reason is that public training data are small, cover few domains, and are usually built from templates, rule-based conversion or expensive proprietary models.

The authors introduce CypherSmith, an instruction-tuning resource generated entirely with open-source LLMs. They rewrite relational schemas from the Text-to-SQL corpus SynSQL-2.5M as property-graph ontologies, so the data inherit its wide domain coverage. Each example also includes an LLM-produced reasoning trace before the target query. Candidate examples first pass syntax and ontology-alignment checks. A likelihood-based filter then compares the query's probability under the full context with its probability when the ontology, question or reasoning is left out, which tests whether each part actually contributes. This filtering needs no real graph and no query execution.

The resulting set is over 12 times larger than earlier public Text-to-Cypher data. Models tuned on it achieve state-of-the-art results on Text2Cypher and CypherBench.

## Key points
- Sources: ontologies are derived from SynSQL-2.5M schemas. CypherSmith is described as the first Text-to-Cypher dataset with reasoning annotations and the first to use LLM likelihoods for filtering synthetic data.
- The likelihood filter beat nine data-selection baselines, including Random, IFD, #InsTag, DEITA, CaR and MIG. Removing the question term P(c|i,o,r) hurt the most, and dropping the reasoning texts also clearly lowered scores.
- The gains transfer to other base models. On CypherBench, a smaller model with a different architecture ("DiffArc-Small") rose from 63.1 to 69.6 EX. A larger model with the same architecture ("SameArc-Large") improved from 43.3 to 61.0 EX and from 80.0 to 99.5 executability.
- On the Text2Cypher test set, BLEU went from 65.2 to 71.9 (DiffArc-Small) and from 70.1 to 76.9 (SameArc-Large) compared with training on Text2Cypher's own data.
- Limitations: the questions are English-only, and both evaluation benchmarks use fairly small knowledge graphs compared with industrial ones.

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

📚 Shelves (4): [🖥️ 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

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 211 works

## Cite

Cite as: Zeyu Zhang, Kexuan Sun, Zheng Tang, Jens-S. Vöckler, Thien Huu Nguyen and Thuy Vu. 2026. CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data. 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{zhang2026cyphersmith,
  title = {{CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data}},
  author = {Zeyu Zhang, Kexuan Sun, Zheng Tang, Jens-S. Vöckler, Thien Huu Nguyen and Thuy Vu},
  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.1601},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1601}
}
```

- [← previous CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models](https://md.research.elamur.ai/free/en/papers/oba-2026-cxmp-linguistic-minimal-pair-benchmark/)
- [next → C³D: Enhancing LLM Reasoning via Confidence-Guided Contrastive Decoding](https://md.research.elamur.ai/free/en/papers/zhang-2026-c-3-d-enhancing-llm/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/)

## References

61 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinheon Baek, Alham Fikri Aji, Jens Lehmann, and Sung Ju Hwang. 2023. Direct fact retrieval from knowledge graphs without entity linking. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Jinheon+Baek%2C+Alham+Fikri+Aji%2C+Jens+Lehmann%2C+and+Sung+Ju+Hwang%2E+2023%2E+Direct+fact+retrieval+from+knowledge+graphs+without+entity+linking%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+f)
2. Debayan Banerjee, Pranav Ajit Nair, Jivat Neet Kaur, Ricardo Usbeck, and Chris Biemann. 2022. Modern baselines for sparql semantic parsing. Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. [find](https://scholar.google.com/scholar?q=Debayan+Banerjee%2C+Pranav+Ajit+Nair%2C+Jivat+Neet+Kaur%2C+Ricardo+Usbeck%2C+and+Chris+Biemann%2E+2022%2E+Modern+baselines+for+sparql+semantic+parsing%2E+Proceedings+of+the+45th+International+ACM+SIGIR+Conference+o)
3. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. [Semantic parsing on Freebase from question-answer pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.
4. Jonathan Berant and Percy Liang. 2014. [Semantic parsing via paraphrasing](https://md.research.elamur.ai/free/en/papers/berant-2014-semantic-parsing-paraphrasing/). In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
5. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIG-MOD International Conference on Management of Data. [find](https://scholar.google.com/scholar?q=Kurt+Bollacker%2C+Colin+Evans%2C+Praveen+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+a+collaboratively+created+graph+database+for+structuring+human+knowledge%2E+In+Proceedings+of+the+2008+ACM+SI)
6. Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, and Haoming Jiang. 2024. Data diversity matters for robust instruction tuning. In Findings of the Association for Computational Linguistics: EMNLP 2024. [find](https://scholar.google.com/scholar?q=Alexander+Bukharin%2C+Shiyang+Li%2C+Zhengyang+Wang%2C+Jingfeng+Yang%2C+Bing+Yin%2C+Xian+Li%2C+Chao+Zhang%2C+Tuo+Zhao%2C+and+Haoming+Jiang%2E+2024%2E+Data+diversity+matters+for+robust+instruction+tuning%2E+In+Findings+of+th)
7. Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, and Hanwang Zhang. 2022. KQA pro: A dataset with explicit compositional programs for complex question answering over knowledge base. In Proceedings of the 60th Annual Meeting of the Association for Computati… [find](https://scholar.google.com/scholar?q=Shulin+Cao%2C+Jiaxin+Shi%2C+Liangming+Pan%2C+Lunyiu+Nie%2C+Yutong+Xiang%2C+Lei+Hou%2C+Juanzi+Li%2C+Bin+He%2C+and+Hanwang+Zhang%2E+2022%2E+KQA+pro%3A+A+dataset+with+explicit+compositional+programs+for+complex+question+answe)
8. Yihan Cao, Yanbin Kang, Chi Wang, and Lichao Sun. 2023. [Instruction mining: Instruction data selection for tuning large language models](https://md.research.elamur.ai/free/en/papers/cao-2023-instruction-mining-instruction-data-selection/). ArXiv, abs/2311.15653.
9. Lichang Chen, Shiyang Li, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, and Hongxia Jin. 2024. [Alpagasus: Training a better alpaca with fewer data](https://md.research.elamur.ai/free/en/papers/chen-2023-alpagasus-training-better-alpaca-fewer/). In The Twelfth International Conference on Learning Representations.
10. Yicheng Chen, Yining Li, Kai Hu, Ma Zerun, HaochenYe HaochenYe, and Kai Chen. 2025. MIG: Automatic data selection for instruction tuning by maximizing information gain in semantic space. In Findings of the Association for Computational Linguistics: ACL 2025. [find](https://scholar.google.com/scholar?q=Yicheng+Chen%2C+Yining+Li%2C+Kai+Hu%2C+Ma+Zerun%2C+HaochenYe+HaochenYe%2C+and+Kai+Chen%2E+2025%2E+MIG%3A+Automatic+data+selection+for+instruction+tuning+by+maximizing+information+gain+in+semantic+space%2E+In+Findings+o)
11. Yongrui Chen, Huiying Li, Yuncheng Hua, and Guilin Qi. 2020. Formal query building with query structure prediction for complex question answering over knowledge base. ArXiv, abs/2109.03614. — [arXiv:2109.03614](https://arxiv.org/abs/2109.03614) [find](https://scholar.google.com/scholar?q=Yongrui+Chen%2C+Huiying+Li%2C+Yuncheng+Hua%2C+and+Guilin+Qi%2E+2020%2E+Formal+query+building+with+query+structure+prediction+for+complex+question+answering+over+knowledge+base%2E+ArXiv%2C+abs%2F2109%2E03614%2E+%E2%80%94+%5BarXiv%3A2)
12. Keyuan Cheng, Gang Lin, Haoyang Fei, Yuxuan Zhai, Lu Yu, Muhammad Asif Ali, Lijie Hu, and Di Wang. 2024. Multi-hop question answering under temporal knowledge editing. ArXiv, abs/2404.00492. — [arXiv:2404.00492](https://arxiv.org/abs/2404.00492) [find](https://scholar.google.com/scholar?q=Keyuan+Cheng%2C+Gang+Lin%2C+Haoyang+Fei%2C+Yuxuan+Zhai%2C+Lu+Yu%2C+Muhammad+Asif+Ali%2C+Lijie+Hu%2C+and+Di+Wang%2E+2024%2E+Multi%2Dhop+question+answering+under+temporal+knowledge+editing%2E+ArXiv%2C+abs%2F2404%2E00492%2E+%E2%80%94+%5BarXiv%3A)
13. Jacopo D’Abramo, Andrea Zugarini, and Paolo Torroni. 2025. Investigating large language models for text-to-SPARQL generation. In Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing. [find](https://scholar.google.com/scholar?q=Jacopo+D%E2%80%99Abramo%2C+Andrea+Zugarini%2C+and+Paolo+Torroni%2E+2025%2E+Investigating+large+language+models+for+text%2Dto%2DSPARQL+generation%2E+In+Proceedings+of+the+4th+International+Workshop+on+Knowledge%2DAugmented+Me)
14. Mohnish Dubey, Debayan Banerjee, Abdelrahman Abdelkawi, and Jens Lehmann. 2019. Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia. In The Semantic Web – ISWC 2019: 18th International Semantic Web Conference, Auckland, New Zealand, October 26–30, 2019, Proceedings,… [find](https://scholar.google.com/scholar?q=Mohnish+Dubey%2C+Debayan+Banerjee%2C+Abdelrahman+Abdelkawi%2C+and+Jens+Lehmann%2E+2019%2E+Lc%2Dquad+2%2E0%3A+A+large+dataset+for+complex+question+answering+over+wikidata+and+dbpedia%2E+In+The+Semantic+Web+%E2%80%93+ISWC+2019%3A+)
15. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. ArXiv, abs/2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+approach+to+query%2Dfocused+summarization%2E+ArXiv%2C)
16. Yanlin Feng, Simone Papicchio, and Sajjadur Rahman. 2025. CypherBench: Towards precise retrieval over full-scale modern knowledge graphs in the LLM era. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Yanlin+Feng%2C+Simone+Papicchio%2C+and+Sajjadur+Rahman%2E+2025%2E+CypherBench%3A+Towards+precise+retrieval+over+full%2Dscale+modern+knowledge+graphs+in+the+LLM+era%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+th)
17. 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)
18. Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, and JingBo Zhu. 2024. Clustering and ranking: Diversity-preserved instruction selection through expert-aligned quality estimation. In Proceedings of the 2024 Conference… [find](https://scholar.google.com/scholar?q=Yuan+Ge%2C+Yilun+Liu%2C+Chi+Hu%2C+Weibin+Meng%2C+Shimin+Tao%2C+Xiaofeng+Zhao%2C+Mahong+Xia%2C+Zhang+Li%2C+Boxing+Chen%2C+Hao+Yang%2C+Bei+Li%2C+Tong+Xiao%2C+and+JingBo+Zhu%2E+2024%2E+Clustering+and+ranking%3A+Diversity%2Dpreserved+in)
19. Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021. Beyond i.i.d.: Three levels of generalization for question answering on knowledge bases. In Proceedings of the Web Conference 2021. [find](https://scholar.google.com/scholar?q=Yu+Gu%2C+Sue+Kase%2C+Michelle+Vanni%2C+Brian+Sadler%2C+Percy+Liang%2C+Xifeng+Yan%2C+and+Yu+Su%2E+2021%2E+Beyond+i%2Ei%2Ed%2E%3A+Three+levels+of+generalization+for+question+answering+on+knowledge+bases%2E+In+Proceedings+of+the+)
20. Jiayan Guo, Lun Du, and Hengyu Liu. 2023. [Gpt4graph: Can large language models understand graph structured data ? an empirical evaluation and benchmarking](https://md.research.elamur.ai/free/en/papers/guo-2023-gpt4graph-large-language-models-understand/). ArXiv, abs/2305.15066.
21. Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2025. GRAG: Graph retrieval-augmented generation. In Findings of the Association for Computational Linguistics: NAACL 2025. [find](https://scholar.google.com/scholar?q=Yuntong+Hu%2C+Zhihan+Lei%2C+Zheng+Zhang%2C+Bo+Pan%2C+Chen+Ling%2C+and+Liang+Zhao%2E+2025%2E+GRAG%3A+Graph+retrieval%2Daugmented+generation%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2025%2E)
22. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, and Ji rong Wen. 2023. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. ArXiv. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Wayne+Xin+Zhao%2C+and+Ji+rong+Wen%2E+2023%2E+Unikgqa%3A+Unified+retrieval+and+reasoning+for+solving+multi%2Dhop+question+answering+over+knowledge+graph%2E+ArXiv%2E)
23. Jiho Kim, Sungjin Park, Yeonsu Kwon, Yohan Jo, James Thorne, and Edward Choi. 2023. FactKG: Fact verification via reasoning on knowledge graphs. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Jiho+Kim%2C+Sungjin+Park%2C+Yeonsu+Kwon%2C+Yohan+Jo%2C+James+Thorne%2C+and+Edward+Choi%2E+2023%2E+FactKG%3A+Fact+verification+via+reasoning+on+knowledge+graphs%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Associ)
24. Liubov Kovriguina, Roman Teucher, Daniil Radyush, and Dmitry Mouromtsev. 2023. Sparqlgen: One-shot prompt-based approach for sparql query generation. In International Conference on Semantic Systems. [find](https://scholar.google.com/scholar?q=Liubov+Kovriguina%2C+Roman+Teucher%2C+Daniil+Radyush%2C+and+Dmitry+Mouromtsev%2E+2023%2E+Sparqlgen%3A+One%2Dshot+prompt%2Dbased+approach+for+sparql+query+generation%2E+In+International+Conference+on+Semantic+Systems%2E)
25. Haoyang Li, Shang Wu, Xiaokang Zhang, Xinmei Huang, Jing Zhang, Fuxin Jiang, Shuai Wang, Tieying Zhang, Jianjun Chen, Rui Shi, Hong Chen, and Cuiping Li. 2025. Omnisql: Synthesizing high-quality text-to-sql data at scale. ArXiv, abs/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+Hong+Chen%2C+and+Cuiping+Li%2E+2025%2E+Omnisql%3A+Synthesizing+high%2Dquality+text%2D)
26. 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/). Proc. ACM Manag. Data.
27. Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, and Jing Xiao. 2024b. [From quantity to quality: Boosting LLM performance with self-guided data selection for instruction tuning](https://md.research.elamur.ai/free/en/papers/li-2023-quantity-quality-boosting-llm-performance/). In Proceedings of the 2024 Conference of the North American Chapter of t…
28. Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su, and Wenhu Chen. 2023. Few-shot in-context learning on knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Tianle+Li%2C+Xueguang+Ma%2C+Alex+Zhuang%2C+Yu+Gu%2C+Yu+Su%2C+and+Wenhu+Chen%2E+2023%2E+Few%2Dshot+in%2Dcontext+learning+on+knowledge+base+question+answering%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association)
29. Yunshui Li, Binyuan Hui, Xiaobo Xia, Jiaxi Yang, Min Yang, Lei Zhang, Shuzheng Si, Ling-Hao Chen, Junhao Liu, Tongliang Liu, Fei Huang, and Yongbin Li. 2024c. [One-shot learning as instruction data prospector for large language models](https://md.research.elamur.ai/free/en/papers/li-2024-one-shot-learning-as-instruction/). In Proceedings of the 62nd Annual Meeting of the Association for…
30. Liangxin Liu, Xuebo Liu, Derek F. Wong, Dongfang Li, Ziyi Wang, Baotian Hu, and Min Zhang. 2024a. Selectit: Selective instruction tuning for llms via uncertainty-aware self-reflection. In Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Liangxin+Liu%2C+Xuebo+Liu%2C+Derek+F%2E+Wong%2C+Dongfang+Li%2C+Ziyi+Wang%2C+Baotian+Hu%2C+and+Min+Zhang%2E+2024a%2E+Selectit%3A+Selective+instruction+tuning+for+llms+via+uncertainty%2Daware+self%2Dreflection%2E+In+Neural+Infor)
31. Shicheng Liu, Sina Semnani, Harold Triedman, Jialiang Xu, Isaac Dan Zhao, and Monica Lam. 2024b. SPINACH: SPARQL-based information navigation for challenging real-world questions. In Findings of the Association for Computational Linguistics: EMNLP 2024. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shicheng+Liu%2C+Sina+Semnani%2C+Harold+Triedman%2C+Jialiang+Xu%2C+Isaac+Dan+Zhao%2C+and+Monica+Lam%2E+2024b%2E+SPINACH%3A+SPARQL%2Dbased+information+navigation+for+challenging+real%2Dworld+questions%2E+In+Findings+of+the+A)
32. Wei Liu, Weihao Zeng, Keqing He, Yong Jiang, and Junxian He. 2024c. [What makes good data for alignment? a comprehensive study of automatic data selection in instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-makes-good-data-alignment-comprehensive/). In The Twelfth International Conference on Learning Representations.
33. Ziche Liu, Rui Ke, Yajiao Liu, Feng Jiang, and Haizhou Li. 2025. Take the essence and discard the dross: A rethinking on data selection for fine-tuning large language models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics… [find](https://scholar.google.com/scholar?q=Ziche+Liu%2C+Rui+Ke%2C+Yajiao+Liu%2C+Feng+Jiang%2C+and+Haizhou+Li%2E+2025%2E+Take+the+essence+and+discard+the+dross%3A+A+rethinking+on+data+selection+for+fine%2Dtuning+large+language+models%2E+In+Proceedings+of+the+202)
34. K. Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, and Chang Zhou. 2024. \[#instag: Instruction tagging for analyzing supervised fine-tuning of large language models](https://md.research.elamur.ai/free/en/papers/lu-2023-instag-instruction-tagging-analyzing-supervised/). In International Conference on Learning Representations.
35. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on graphs: Faithful and interpretable large language model reasoning. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2024%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+In+International+Conference+on+Learning+Representati)
36. Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, and Jianfeng Gao. 2022. Open domain question answering with a unified knowledge interface. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kaixin+Ma%2C+Hao+Cheng%2C+Xiaodong+Liu%2C+Eric+Nyberg%2C+and+Jianfeng+Gao%2E+2022%2E+Open+domain+question+answering+with+a+unified+knowledge+interface%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association)
37. Seungwhan Moon, Pararth Shah, Anuj Kumar, and Rajen Subba. 2019. [OpenDialKG: Explainable conversational reasoning with attention-based walks over knowledge graphs](https://md.research.elamur.ai/free/en/papers/moon-2019-opendialkg-explainable-conversational-reasoning-attention/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
38. Lunyiu Nie, Shulin Cao, Jiaxin Shi, Jiuding Sun, Qi Tian, Lei Hou, Juanzi Li, and Jidong Zhai. 2022. GraphQ IR: Unifying the semantic parsing of graph query languages with one intermediate representation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Lunyiu+Nie%2C+Shulin+Cao%2C+Jiaxin+Shi%2C+Jiuding+Sun%2C+Qi+Tian%2C+Lei+Hou%2C+Juanzi+Li%2C+and+Jidong+Zhai%2E+2022%2E+GraphQ+IR%3A+Unifying+the+semantic+parsing+of+graph+query+languages+with+one+intermediate+representat)
39. Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, and Scott Yih. 2022. [UniK-QA: Unified representations of structured and unstructured knowledge for open-domain question answering](https://md.research.elamur.ai/free/en/papers/oguz-2022-unik-qa-unified-representations-structured/). In Findings of the Association for Comp…
40. 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). [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)
41. Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan Ö. Arik. 2024. Chase-sql: Multi-path reasoning and preference optimized candidate selection in text-to-sql. ArXiv, abs/2410.01943. — [arXiv:2410.01943](https://arxiv.org/abs/2410.01943) [find](https://scholar.google.com/scholar?q=Mohammadreza+Pourreza%2C+Hailong+Li%2C+Ruoxi+Sun%2C+Yeounoh+Chung%2C+Shayan+Talaei%2C+Gaurav+Tarlok+Kakkar%2C+Yu+Gan%2C+Amin+Saberi%2C+Fatma+Ozcan%2C+and+Sercan+%C3%96%2E+Arik%2E+2024%2E+Chase%2Dsql%3A+Multi%2Dpath+reasoning+and+prefer)
42. Chang Su, Jiexing Qi, He Yan, Kai Zou, and Zhouhan Lin. 2024. Enhancing sparql generation by triplet-order-sensitive pre-training. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. [find](https://scholar.google.com/scholar?q=Chang+Su%2C+Jiexing+Qi%2C+He+Yan%2C+Kai+Zou%2C+and+Zhouhan+Lin%2E+2024%2E+Enhancing+sparql+generation+by+triplet%2Dorder%2Dsensitive+pre%2Dtraining%2E+Proceedings+of+the+33rd+ACM+International+Conference+on+Information+a)
43. Yu Su, Huan Sun, Brian Sadler, Mudhakar Srivatsa, Izzeddin Gür, Zenghui Yan, and Xifeng Yan. 2016. On generating characteristic-rich question sets for QA evaluation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Yu+Su%2C+Huan+Sun%2C+Brian+Sadler%2C+Mudhakar+Srivatsa%2C+Izzeddin+G%C3%BCr%2C+Zenghui+Yan%2C+and+Xifeng+Yan%2E+2016%2E+On+generating+characteristic%2Drich+question+sets+for+QA+evaluation%2E+In+Proceedings+of+the+2016+Confere)
44. Alon Talmor and Jonathan Berant. 2018. [The web as a knowledge-base for answering complex questions](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers).
45. 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+)
46. Ricardo Usbeck, Ria Hari Gusmita, Axel-Cyrille Ngonga Ngomo, and Muhammad Saleem. 2018. 9th challenge on question answering over linked data (qald-9) (invited paper). In Semdeep/NLIWoD@ISWC. [find](https://scholar.google.com/scholar?q=Ricardo+Usbeck%2C+Ria+Hari+Gusmita%2C+Axel%2DCyrille+Ngonga+Ngomo%2C+and+Muhammad+Saleem%2E+2018%2E+9th+challenge+on+question+answering+over+linked+data+%28qald%2D9%29+%28invited+paper%29%2E+In+Semdeep%2FNLIWoD%40ISWC%2E)
47. 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.
48. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, and Zhoujun Li. 2025. [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/). In Proceedings of the 31st International Conference on Computational Linguistics.
49. Peiqi Wang, Yikang Shen, Zhen Guo, Matt Stallone, Yoon Kim, Polina Golland, and Rameswar Panda. 2024. Diversity measurement and subset selection for instruction tuning datasets. ArXiv, abs/2402.02318. [find](https://scholar.google.com/scholar?q=Peiqi+Wang%2C+Yikang+Shen%2C+Zhen+Guo%2C+Matt+Stallone%2C+Yoon+Kim%2C+Polina+Golland%2C+and+Rameswar+Panda%2E+2024%2E+Diversity+measurement+and+subset+selection+for+instruction+tuning+datasets%2E+ArXiv%2C+abs%2F2402%2E02318%2E)
50. Shengguang Wu, Keming Lu, Benfeng Xu, Junyang Lin, Qi Su, and Chang Zhou. 2023. Self-evolved diverse data sampling for efficient instruction tuning. arXiv preprint arXiv:2311.08182. — [arXiv:2311.08182](https://arxiv.org/abs/2311.08182) [find](https://scholar.google.com/scholar?q=Shengguang+Wu%2C+Keming+Lu%2C+Benfeng+Xu%2C+Junyang+Lin%2C+Qi+Su%2C+and+Chang+Zhou%2E+2023%2E+Self%2Devolved+diverse+data+sampling+for+efficient+instruction+tuning%2E+arXiv+preprint+arXiv%3A2311%2E08182%2E+%E2%80%94+%5BarXiv%3A2311%2E0818)
51. Shirley Wu, Shiyu Zhao, Michihiro Yasunaga, Kexin Huang, Kaidi Cao, Qian Huang, Vassilis N. Ioannidis, Karthik Subbian, James Zou, and Jure Leskovec. 2024. Stark: Benchmarking llm retrieval on textual and relational knowledge bases. ArXiv, abs/2404.13207. [find](https://scholar.google.com/scholar?q=Shirley+Wu%2C+Shiyu+Zhao%2C+Michihiro+Yasunaga%2C+Kexin+Huang%2C+Kaidi+Cao%2C+Qian+Huang%2C+Vassilis+N%2E+Ioannidis%2C+Karthik+Subbian%2C+James+Zou%2C+and+Jure+Leskovec%2E+2024%2E+Stark%3A+Benchmarking+llm+retrieval+on+textual)
52. Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, Sanjeev Arora, and Danqi Chen. 2024. [Less: selecting influential data for targeted instruction tuning](https://md.research.elamur.ai/free/en/papers/xia-2024-less-selecting-influential-data-targeted/). In Proceedings of the 41st International Conference on Machine Learning.
53. Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Wang, Zhiguo Wang, and Bing Xiang. 2023. Decaf: Joint decoding of answers and logical forms for question answering over knowledge bases. International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Donghan+Yu%2C+Sheng+Zhang%2C+Patrick+Ng%2C+Henghui+Zhu%2C+Alexander+Hanbo+Li%2C+Jun+Wang%2C+Yiqun+Hu%2C+William+Wang%2C+Zhiguo+Wang%2C+and+Bing+Xiang%2E+2023%2E+Decaf%3A+Joint+decoding+of+answers+and+logical+forms+for+questi)
54. Yi Zhang, Jan Deriu, George Katsogiannis-Meimarakis, Catherine Kosten, Georgia Koutrika, and Kurt Stockinger. 2023. Sciencebenchmark: A complex real-world benchmark for evaluating natural language to sql systems. Proc. VLDB Endow. [find](https://scholar.google.com/scholar?q=Yi+Zhang%2C+Jan+Deriu%2C+George+Katsogiannis%2DMeimarakis%2C+Catherine+Kosten%2C+Georgia+Koutrika%2C+and+Kurt+Stockinger%2E+2023%2E+Sciencebenchmark%3A+A+complex+real%2Dworld+benchmark+for+evaluating+natural+language+to+)
55. Ziyu Zhao, Wei Liu, Tim French, and Michael Stewart. 2023a. Cyspider: A neural semantic parsing corpus with baseline models for property graphs. In AI 2023: Advances in Artificial Intelligence: 36th Australasian Joint Conference on Artificial Intelligence, AI 2023, Brisbane, QLD, Australia, November… [find](https://scholar.google.com/scholar?q=Ziyu+Zhao%2C+Wei+Liu%2C+Tim+French%2C+and+Michael+Stewart%2E+2023a%2E+Cyspider%3A+A+neural+semantic+parsing+corpus+with+baseline+models+for+property+graphs%2E+In+AI+2023%3A+Advances+in+Artificial+Intelligence%3A+36th+A)
56. Ziyu Zhao, Wei Liu, Tim French, and Michael Stewart. 2023b. Rel2graph: Automated mapping from relational databases to a unified property knowledge graph. arXiv preprint arXiv:2310.01080. — [arXiv:2310.01080](https://arxiv.org/abs/2310.01080) [find](https://scholar.google.com/scholar?q=Ziyu+Zhao%2C+Wei+Liu%2C+Tim+French%2C+and+Michael+Stewart%2E+2023b%2E+Rel2graph%3A+Automated+mapping+from+relational+databases+to+a+unified+property+knowledge+graph%2E+arXiv+preprint+arXiv%3A2310%2E01080%2E+%E2%80%94+%5BarXiv%3A2310)
57. Zijie Zhong, Linqing Zhong, Zhaoze Sun, Qingyun Jin, Zengchang Qin, and Xiaofan Zhang. 2025. Syn-theT2C: Generating synthetic data for fine-tuning large language models on the Text2Cypher task. In Proceedings of the 31st International Conference on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zijie+Zhong%2C+Linqing+Zhong%2C+Zhaoze+Sun%2C+Qingyun+Jin%2C+Zengchang+Qin%2C+and+Xiaofan+Zhang%2E+2025%2E+Syn%2DtheT2C%3A+Generating+synthetic+data+for+fine%2Dtuning+large+language+models+on+the+Text2Cypher+task%2E+In+Pro)
58. Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023. Lima: less is more for alignment. In Proceedings of the 37th International Conference on Neural Information Pr… [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srini+Iyer%2C+Jiao+Sun%2C+Yuning+Mao%2C+Xuezhe+Ma%2C+Avia+Efrat%2C+Ping+Yu%2C+Lili+Yu%2C+Susan+Zhang%2C+Gargi+Ghosh%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Omer+Levy%2E+2023%2E+Lima%3A+less)
59. Huangchao Xu, Baohua Zhang, Zhong Jin, Tiannian Zhu, Quansheng Wu, and Hongming Weng. 2024. Enhancing large language models with domain-specific knowledge: The case in topological materials. volume abs/2409.13732v1. — [arXiv:2409.13732](https://arxiv.org/abs/2409.13732) [find](https://scholar.google.com/scholar?q=Huangchao+Xu%2C+Baohua+Zhang%2C+Zhong+Jin%2C+Tiannian+Zhu%2C+Quansheng+Wu%2C+and+Hongming+Weng%2E+2024%2E+Enhancing+large+language+models+with+domain%2Dspecific+knowledge%3A+The+case+in+topological+materials%2E+volume+ab)
60. Silei Xu, Shicheng Liu, Theo Culhane, Elizaveta Pert-seva, Meng-Hsi Wu, Sina Semnani, and Monica Lam. 2023. Fine-tuned LLMs know more, hallucinate less with few-shot sequence-to-sequence semantic parsing over Wikidata. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Pr… [find](https://scholar.google.com/scholar?q=Silei+Xu%2C+Shicheng+Liu%2C+Theo+Culhane%2C+Elizaveta+Pert%2Dseva%2C+Meng%2DHsi+Wu%2C+Sina+Semnani%2C+and+Monica+Lam%2E+2023%2E+Fine%2Dtuned+LLMs+know+more%2C+hallucinate+less+with+few%2Dshot+sequence%2Dto%2Dsequence+semantic+pars)
61. Wen-tau Yih, Matthew Richardson, Chris Meek, Ming-Wei Chang, and Jina Suh. 2016. [The value of semantic parse labeling for knowledge base question answering](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

*Updated 2 November 2026*