{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:59:25Z","timestamp":1772906365257,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819794331","type":"print"},{"value":"9789819794348","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9434-8_35","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"449-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Finetuning LLMs for\u00a0Text-to-SQL with\u00a0Two-Stage Progressive Learning"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Ling","sequence":"first","affiliation":[]},{"given":"Jialin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jindu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"35_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"35_CR2","unstructured":"Chen, X., Lin, M., Sch\u00e4rli, N., Zhou, D.: Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128 (2023)"},{"key":"35_CR3","unstructured":"Dong, X., et\u00a0al.: C3: zero-shot text-to-sql with chatgpt. arXiv preprint arXiv:2307.07306 (2023)"},{"key":"35_CR4","unstructured":"Dou, L., et al.: Unisar: a unified structure-aware autoregressive language model for text-to-sql. arXiv preprint arXiv:2203.07781 (2022)"},{"key":"35_CR5","unstructured":"Gao, D., et al.: Text-to-sql empowered by large language models: a benchmark evaluation. arXiv preprint arXiv:2308.15363 (2023)"},{"key":"35_CR6","unstructured":"Guo, D., et\u00a0al.: Deepseek-coder: when the large language model meets programming\u2013the rise of code intelligence. arXiv preprint arXiv:2401.14196 (2024)"},{"key":"35_CR7","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"35_CR8","unstructured":"Lee, D., Park, C., Kim, J., Park, H.: Mcs-sql: leveraging multiple prompts and multiple-choice selection for text-to-sql generation. arXiv preprint arXiv:2405.07467 (2024)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, J., Li, C., Chen, H.: Resdsql: decoupling schema linking and skeleton parsing for text-to-sql. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13067\u201313075 (2023)","DOI":"10.1609\/aaai.v37i11.26535"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Codes: towards building open-source language models for text-to-sql. In: Proceedings of the ACM on Management of Data, vol. 2, no. 3, pp. 1\u201328 (2024)","DOI":"10.1145\/3654930"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Graphix-t5: mixing pre-trained transformers with graph-aware layers for text-to-sql parsing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13076\u201313084 (2023)","DOI":"10.1609\/aaai.v37i11.26536"},{"key":"35_CR13","unstructured":"Li, J., et\u00a0al.: Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"35_CR14","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"35_CR15","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR16","unstructured":"Pourreza, M., Rafiei, D.: Din-sql: decomposed in-context learning of text-to-sql with self-correction. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Pourreza, M., Rafiei, D.: Dts-sql: decomposed text-to-sql with small large language models. arXiv preprint arXiv:2402.01117 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Qi, J., 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"},{"issue":"140","key":"35_CR19","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR20","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":"35_CR21","doi-asserted-by":"crossref","unstructured":"Suhr, A., Chang, M.W., Shaw, P., Lee, K.: Exploring unexplored generalization challenges for cross-database semantic parsing. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8372\u20138388 (2020)","DOI":"10.18653\/v1\/2020.acl-main.742"},{"key":"35_CR22","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"35_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"35_CR24","unstructured":"Wang, B., et al.: Mac-sql: multi-agent collaboration for text-to-sql. arXiv preprint arXiv:2312.11242 (2023)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Yu, T., et\u00a0al.: Spider: a large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3911\u20133921 (2018)","DOI":"10.18653\/v1\/D18-1425"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9434-8_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:55:29Z","timestamp":1732982129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9434-8_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794331","9789819794348"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9434-8_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}