Page 371 - 《软件学报》2026年第2期

850 软件学报 2026 年第 37 卷第 2 期

[57] Tai CY, Chen ZR, Zhang TS, Deng X, Sun H. Exploring chain-of-thought style prompting for text-to-SQL. arXiv:2305.14215, 2023.
[58] Zhang HC, Cao RS, Chen L, Xu HS, Yu K. ACT-SQL: In-context learning for text-to-SQL with automatically-generated chain-of-
thought. In: Proc. of the 2023 Findings of the Association for Computational Linguistics. Singapore: Association for Computational
Linguistics, 2023. 3501–3532. [doi: 10.18653/v1/2023.findings-emnlp.227]
[59] Sun RX, Arik SÖ, Muzio A, Miculicich L, Gundabathula S, Yin PC, Dai HJ, Nakhost H, Sinha R, Wang ZF, Pfister T. SQL-PaLM:
Improved large language model adaptation for text-to-SQL (extended). arXiv:2306.00739, 2024.
[60] Shi FD, Fried D, Ghazvininejad M, Zettlemoyer L, Wang SI. Natural language to code translation with execution. In: Proc. of the 2022
Conf. on Empirical Methods in Natural Language Processing. Abu Dhabi: Association for Computational Linguistics, 2022. 3533–3546.
[doi: 10.18653/v1/2022.emnlp-main.231]
[61] Dong XM, Zhang C, Ge YH, Mao YR, Gao YJ, Chen L, Lin JS, Lou DF. C3: Zero-shot text-to-SQL with ChatGPT. arXiv:2307.07306,
2023.
[62] Gao DW, Wang HB, Li YL, Sun XY, Qian YC, Ding BL, Zhou JR. Text-to-SQL empowered by large language models: A benchmark
evaluation. Proc. of the VLDB Endowment, 2024, 17(5): 1132–1145. [doi: 10.14778/3641204.364122]
[63] Li HY, Zhang J, Liu HB, Fan J, Zhang XK, Zhu J, Wei RJ, Pan HY, Li CP, Chen H. CodeS: Towards building open-source language
models for text-to-SQL. Proc. of the ACM on Management of Data, 2024, 2(3): 127. [doi: 10.1145/3654930]
[64] Liu YH, Han TL, Ma SY, Zhang JY, Yang YY, Tian JM, He H, Li AT, He MS, Liu ZL, Wu ZH, Zhao L, Zhu DJ, Li X, Qiang N, Shen
DG, Liu TM, Ge B. Summary of ChatGPT-related research and perspective towards the future of large language models. Meta-
Radiology, 2023, 1(2): 100017. [doi: 10.1016/j.metrad.2023.100017]
[65] Zha L, Zhou J, Li L, Wang R, Huang Q, Yang S, Yuan J, Su C, Li X, Su A, Zhang T, Zhou C, Shou K, Wang M, Zhu W, Lu G, Ye C,
Ye Y, Ye W, Zhang Y, Deng X, Xu J, Wang H, Chen G, Zhao J. TableGPT: Towards unifying tables, nature language and commands
into one GPT. arXiv:2307.08674, 2023.
[66] Deng Y, Lei WQ, Zhang WX, Lam W, Chua TS. PACIFIC: Towards proactive conversational question answering over tabular and
textual data in finance. In: Proc. of the 2022 Conf. on Empirical Methods in Natural Language Processing. Abu Dhabi: Association for
Computational Linguistics, 2022. 6970–6984. [doi: 10.18653/v1/2022.emnlp-main.469]
[67] Zhao YL, Long YT, Liu HJ, Kamoi R, Nan LY, Chen LH, Liu YX, Tang XR, Zhang R, Cohan A. DocMath-eval: Evaluating math
reasoning capabilities of LLMs in understanding long and specialized documents. In: Proc. of the 62nd Annual Meeting of the
Association for Computational Linguistics. Bangkok: Association for Computational Linguistics, 2024. 16103–16120. [doi: 10.18653/v1/
2024.acl-long.852]
[68] Sui Y, Zou JR, Zhou MY, He XY, Du L, Han S, Zhang DM. TAP4LLM: Table provider on sampling, augmenting, and packing semi-
structured data for large language model reasoning. In: Proc. of the 2024 Findings of the Association for Computational Linguistics.
Miami: Association for Computational Linguistics, 2024. 10306–10323. [doi: 10.18653/v1/2024.findings-emnlp.603]
[69] Sundar AS, Heck L. cTBLS: Augmenting large language models with conversational tables. In: Proc. of the 5th Workshop on NLP for
Conversational AI. Toronto: Association for Computational Linguistics, 2023. 59–70. [doi: 10.18653/v1/2023.nlp4convai-1.6]
[70] Ye JJ, Chen XT, Xu N, Zu C, Shao ZK, Liu SC, Cui YH, Zhou ZY, Gong C, Shen Y, Zhou J, Chen SM, Gui T, Zhang Q, Huang XJ. A
comprehensive capability analysis of GPT-3 and GPT-3.5 series models. arXiv:2303.10420, 2023.
[71] Sui Y, Zhou MY, Zhou MJ, Han S, Zhang DM. Table meets LLM: Can large language models understand structured table data? A
benchmark and empirical study. In: Proc. of the 17th ACM Int’l Conf. on Web Search and Data Mining. Mexico: ACM, 2024. 645–654.
[doi: 10.1145/3616855.3635752]
[72] Yu T, Zhang R, Yasunaga M, Tan YC, Lin XV, Li SY, Er HY, Li I, Pang B, Chen T, Ji E, Dixit S, Proctor D, Shim S, Kraft J, Zhang V,
Xiong CM, Socher R, Radev D. SParC: Cross-domain semantic parsing in context. In: Proc. of the 57th Annual Meeting of the
Association for Computational Linguistics. Florence: Association for Computational Linguistics, 2019. 4511–4523. [doi: 10.18653/v1/
P19-1443]
[73] Weng LX, Tang YH, Feng YCJ, Chang Z, Chen RQ, Feng HZ, Hou C, Huang DQ, Li Y, Rao HN, Wang HM, Wei CS, Yang XF, Zhang
YH, Zheng YF, Huang XQ, Zhu MF, Ma YX, Cui B, Chen P, Chen W. DataLab: A unified platform for LLM-powered business
intelligence. In: Proc. of the 41st IEEE Int’l Conf. on Data Engineering. Hong Kong: IEEE, 2025. 4346–4359. [doi: 10.1109/ICDE65448.
2025.00326]
[74] Katsogiannis-Meimarakis G, Koutrika G. A survey on deep learning approaches for text-to-SQL. The VLDB Journal, 2023, 32(4):
905–936. [doi: 10.1007/s00778-022-00776-8]
[75] Deng NH, Chen YL, Zhang Y. Recent advances in text-to-SQL: A survey of what we have and what we expect. In: Proc. of the 29th Int’l
Conf. on Computational Linguistics. Gyeongju: Int’l Committee on Computational Linguistics, 2022. 2166–2187.