{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:37:00Z","timestamp":1757619420279,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500130"},{"type":"electronic","value":"9789819500147"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-95-0014-7_5","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T10:05:20Z","timestamp":1753351520000},"page":"52-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Based Data Synthesis and Distillation for High-Quality Text-to-SQL Training"],"prefix":"10.1007","author":[{"given":"Shaoguo","family":"Cui","sequence":"first","affiliation":[]},{"given":"Keying","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Binbin","family":"Sang","sequence":"additional","affiliation":[]},{"given":"Tiansong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huan","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Wang, B., Shin, R., Liu, X., et al.: RAT-SQL: relation-aware schema encoding and linking for Text-to-SQL parsers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7567\u20137578 (2020)","DOI":"10.18653\/v1\/2020.acl-main.677"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Scholak, T., Schucher, N., Bahdanau, D.: PICARD: parsing incrementally for constrained auto-regressive decoding from language models. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 9895\u20139901 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.779"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Hu, Y., Zhao, Y., Jiang, J., et al.: Importance of synthesizing high-quality data for text-to-SQL parsing. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 1327\u20131343 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.86"},{"issue":"5","key":"5_CR4","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.14778\/3641204.3641221","volume":"17","author":"D Gao","year":"2024","unstructured":"Gao, D., Wang, H., Li, Y., et al.: Text-to-SQL empowered by large language models: a benchmark evaluation. Proc. VLDB Endow. 17(5), 1132\u20131145 (2024)","journal-title":"Proc. VLDB Endow."},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Yu, T., Zhang, R., Yang, K., et al.: Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and Text-to-SQL task. In: 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), pp. 3911\u20133921. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1425"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Feng, S.Y., Gangal, V., Wei, J., et al.: A survey of data augmentation approaches for NLP. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 968\u2013988 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"5_CR7","unstructured":"Meng, Y., Michalski, M., Huang, J., et al.: Tuning language models as training data generators for augmentation-enhanced few-shot learning. In: International Conference on Machine Learning, pp. 24457\u201324477. PMLR (2023)"},{"key":"5_CR8","unstructured":"Gao, J., Pi, R., Yong, L., et al.: Self-guided noise-free data generation for efficient zero-shot learning. In: Proceedings of the International Conference on Learning Representations (2023)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Long, L., Wang, R., Xiao, R., et al.: On LLMs-driven synthetic data generation, curation, and evaluation: a survey. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 11065\u201311082 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.658"},{"key":"5_CR10","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., Chiang, W.L., Sheng, Y., et al.: Judging LLM-as-a-judge with MT-bench and Chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR11","unstructured":"Yang, A., Yang, B., Zhang, B., et al.: Qwen2.5 Technical Report (2024). arXiv preprint arXiv:2412.15115"},{"key":"5_CR12","unstructured":"Guo, D., Yang, D., Zhang, H., et al.: Deepseek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025). arXiv preprint arXiv:2501.12948"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"He, X., Lin, Z., Gong, Y., et al.: AnnoLLM: making large language models to be better crowdsourced annotators. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pp. 165\u2013190 (2024)","DOI":"10.18653\/v1\/2024.naacl-industry.15"},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"4957","DOI":"10.1109\/TPAMI.2024.3362821","volume":"46","author":"I Joshi","year":"2024","unstructured":"Joshi, I., Grimmer, M., Rathgeb, C., et al.: Synthetic data in human analysis: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46, 4957\u20134976 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"240","key":"5_CR15","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., Narang, S., Devlin, J., et al.: PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR16","first-page":"55006","volume":"36","author":"C Zhou","year":"2023","unstructured":"Zhou, C., Liu, P., Xu, P., et al.: LIMA: less is more for alignment. Adv. Neural. Inf. Process. Syst. 36, 55006\u201355021 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, J., Li, C., et al.: ResdSQL: decoupling schema linking and skeleton parsing for Text-to-SQL. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 11, pp. 13067\u201313075 (2023)","DOI":"10.1609\/aaai.v37i11.26535"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Gan, Y., Chen, X., Purver, M.: Exploring underexplored limitations of cross-domain Text-to-SQL generalization. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8926\u20138931 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.702"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Gan, Y., Chen, X., Huang, Q., et al.: Towards robustness of Text-to-SQL models against synonym substitution. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 2505\u20132515 (2021)","DOI":"10.18653\/v1\/2021.acl-long.195"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Deng, X., Hassan, A., Meek, C., et al.: Structure-grounded pretraining for text-to-SQL. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1337\u20131350 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.105"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Qi, J., Tang, J., He, Z., et al.: RASAT: Integrating relational structures into pretrained Seq2Seq model for Text-to-SQL. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3215\u20133229 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.211"},{"key":"5_CR22","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., et al.: Code Llama: Open foundation models for code (2023). arXiv preprint arXiv:2308.12950"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0014-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T21:35:31Z","timestamp":1757280931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0014-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500130","9789819500147"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0014-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}