{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:04:31Z","timestamp":1773295471688,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1145\/3639477.3639732","type":"proceedings-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T13:27:26Z","timestamp":1717162046000},"page":"252-262","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Enhancing Text-to-SQL Translation for Financial System Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6314-7515","authenticated-orcid":false,"given":"Yewei","family":"Song","sequence":"first","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7657-4738","authenticated-orcid":false,"given":"Saad","family":"Ezzini","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2831-6472","authenticated-orcid":false,"given":"Xunzhu","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5372-7970","authenticated-orcid":false,"given":"Cedric","family":"Lothritz","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4052-475X","authenticated-orcid":false,"given":"Jacques","family":"Klein","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7270-9869","authenticated-orcid":false,"given":"Tegawende","family":"Bissyande","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1166-5908","authenticated-orcid":false,"given":"Andrey","family":"Boytsov","sequence":"additional","affiliation":[{"name":"Banque BGL BNP Paribas, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8805-8654","authenticated-orcid":false,"given":"Ulrick","family":"Ble","sequence":"additional","affiliation":[{"name":"Banque BGL BNP Paribas, Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2734-7422","authenticated-orcid":false,"given":"Anne","family":"Goujon","sequence":"additional","affiliation":[{"name":"Banque BGL BNP Paribas, Luxembourg, Luxembourg"}]}],"member":"320","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 2397--2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397--2430."},{"key":"e_1_3_2_1_2_1","volume-title":"Yuanzhi Li, Scott Lundberg, et al.","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075823"},{"key":"e_1_3_2_1_4_1","unstructured":"Beeching Edward Fourrier Cl\u00e9mentine Habib Nathan Han Sheon Lambert Nathan Rajani Nazneen Sanseviero Omar Tunstall Lewis and Wolf Thomas. 2023. Open LLM Leaderboard. https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard."},{"key":"e_1_3_2_1_5_1","volume-title":"Koala: A Dialogue Model for Academic Research. Blog post. https:\/\/bair.berkeley.edu\/blog\/2023\/04\/03\/koala\/","author":"Geng Xinyang","year":"2023","unstructured":"Xinyang Geng, Arnav Gudibande, Hao Liu, Eric Wallace, Pieter Abbeel, Sergey Levine, and Dawn Song. 2023. Koala: A Dialogue Model for Academic Research. Blog post. https:\/\/bair.berkeley.edu\/blog\/2023\/04\/03\/koala\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"e_1_3_2_1_7_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"d.]. Huggingface Leaderboard. https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard last accessed","year":"2023","unstructured":"Huggingface. [n. d.]. Huggingface Leaderboard. https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard last accessed: May 2023."},{"key":"e_1_3_2_1_10_1","volume-title":"A survey on deep learning approaches for text-to-SQL. The VLDB Journal","author":"Katsogiannis-Meimarakis George","year":"2023","unstructured":"George Katsogiannis-Meimarakis and Georgia Koutrika. 2023. A survey on deep learning approaches for text-to-SQL. The VLDB Journal (2023), 1--32."},{"key":"e_1_3_2_1_11_1","volume-title":"Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries.","author":"Kocetkov Denis","year":"2022","unstructured":"Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Mu\u00f1oz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, and Harm de Vries. 2022. The Stack: 3 TB of permissively licensed source code. Preprint (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"Oliver Stanley, Rich\u00e1rd Nagyfi, et al.","author":"K\u00f6pf Andreas","year":"2023","unstructured":"Andreas K\u00f6pf, Yannic Kilcher, Dimitri von R\u00fctte, Sotiris Anagnostidis, Zhi-Rui Tam, Keith Stevens, Abdullah Barhoum, Nguyen Minh Duc, Oliver Stanley, Rich\u00e1rd Nagyfi, et al. 2023. OpenAssistant Conversations-Democratizing Large Language Model Alignment. arXiv preprint arXiv:2304.07327 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.2006.18"},{"key":"e_1_3_2_1_14_1","unstructured":"Numbers Station Labs. 2023. NSText2SQL: An Open Source Text-to-SQL Dataset for Foundation Model Training. https:\/\/github.com\/NumbersStationAI\/NSQL"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26535"},{"key":"e_1_3_2_1_16_1","volume-title":"Graphix-t5: Mixing pre-trained transformers with graph-aware layers for text-to-sql parsing. arXiv preprint arXiv:2301.07507","author":"Li Jinyang","year":"2023","unstructured":"Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, and Yongbin Li. 2023. Graphix-t5: Mixing pre-trained transformers with graph-aware layers for text-to-sql parsing. arXiv preprint arXiv:2301.07507 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Zhengxiao Du, Zhilin Yang, and Jie Tang.","author":"Liu Xiao","year":"2022","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2022. P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. arXiv:2110.07602 [cs.CL]"},{"key":"e_1_3_2_1_19_1","volume-title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4. arXiv:2306.02707 [cs.CL]","author":"Mukherjee Subhabrata","year":"2023","unstructured":"Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, and Ahmed Awadallah. 2023. Orca: Progressive Learning from Complex Explanation Traces of GPT-4. arXiv:2306.02707 [cs.CL]"},{"key":"e_1_3_2_1_20_1","volume-title":"Codegen2: Lessons for training llms on programming and natural languages. arXiv preprint arXiv:2305.02309","author":"Nijkamp Erik","year":"2023","unstructured":"Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, and Yingbo Zhou. 2023. Codegen2: Lessons for training llms on programming and natural languages. arXiv preprint arXiv:2305.02309 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699485"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2015.08.004"},{"key":"e_1_3_2_1_24_1","unstructured":"Bowen Qin Binyuan Hui Lihan Wang Min Yang Jinyang Li Binhua Li Ruiying Geng Rongyu Cao Jian Sun Luo Si et al. 2022. A survey on text-to-sql parsing: Concepts methods and future directions. arXiv preprint arXiv:2208.13629 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093","author":"Scholak Torsten","year":"2021","unstructured":"Torsten Scholak, Nathan Schucher, and Dzmitry Bahdanau. 2021. PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_27_1","unstructured":"MosaicML NLP Team. 2023. Introducing MPT-7B: A New Standard for Open-Source Commercially Usable LLMs. www.mosaicml.com\/blog\/mpt-7b Accessed: 2023-05-05."},{"key":"e_1_3_2_1_28_1","volume-title":"Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, and Tegawend\u00e9 F Bissyand\u00e9.","author":"Tian Haoye","year":"2023","unstructured":"Haoye Tian, Weiqi Lu, Tsz On Li, Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, and Tegawend\u00e9 F Bissyand\u00e9. 2023. Is ChatGPT the Ultimate Programming Assistant-How far is it? arXiv preprint arXiv:2304.11938 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_32_1","volume-title":"Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, et al.","author":"Yu Tao","year":"2019","unstructured":"Tao Yu, Rui Zhang, He Yang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, et al. 2019. Cosql: A conversational text-to-sql challenge towards cross-domain natural language interfaces to databases. arXiv preprint arXiv:1909.05378 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. arXiv preprint arXiv:1809.08887","author":"Yu Tao","year":"2018","unstructured":"Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. arXiv preprint arXiv:1809.08887 (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"Seq2sql: Generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103","author":"Zhong Victor","year":"2017","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2sql: Generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103 (2017)."}],"event":{"name":"ICSE-SEIP '24: 46th International Conference on Software Engineering: Software Engineering in Practice","location":"Lisbon Portugal","acronym":"ICSE-SEIP '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639477.3639732","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639477.3639732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:31Z","timestamp":1750290271000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639477.3639732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":34,"alternative-id":["10.1145\/3639477.3639732","10.1145\/3639477"],"URL":"https:\/\/doi.org\/10.1145\/3639477.3639732","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}