{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T07:29:57Z","timestamp":1783754997095,"version":"3.55.0"},"reference-count":152,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["25208322"],"award-info":[{"award-number":["25208322"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502008"],"award-info":[{"award-number":["62502008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funding Scheme for Research and Innovation of FDCT","award":["0021\/2025\/ITP1"],"award-info":[{"award-number":["0021\/2025\/ITP1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tkde.2025.3609486","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:31:52Z","timestamp":1757698312000},"page":"7328-7345","source":"Crossref","is-referenced-by-count":61,"title":["Next-Generation Database Interfaces: A Survey of LLM-Based Text-to-SQL"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2283-255X","authenticated-orcid":false,"given":"Zijin","family":"Hong","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9231-2607","authenticated-orcid":false,"given":"Zheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0247-4942","authenticated-orcid":false,"given":"Qinggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6816-5344","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Macau, Macau SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2117-6083","authenticated-orcid":false,"given":"Junnan","family":"Dong","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-0212","authenticated-orcid":false,"given":"Feiran","family":"Huang","sequence":"additional","affiliation":[{"name":"Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3867-900X","authenticated-orcid":false,"given":"Xiao","family":"Huang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"42330","article-title":"Can LLM already serve as a database interface? A BIg bench for large-scale database grounded text-to-SQLs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539305"},{"key":"ref3","article-title":"A survey on text-to-SQL parsing: Concepts, methods, and future directions","author":"Qin","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref6","article-title":"Evaluating the text-to-SQL capabilities of large language models","author":"Rajkumar","year":"2022"},{"key":"ref7","first-page":"36339","article-title":"DIN-SQL: Decomposed in-context learning of text-to-SQL with self-correction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pourreza"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641221"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14778\/2735461.2735468"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/EICT.2015.7391926"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1425"},{"key":"ref12","article-title":"Seq2SQL: Generating structured queries from natural language using reinforcement learning","author":"Zhong","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.99"},{"key":"ref14","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"Improving text-to-SQL with schema dependency learning","author":"Hui","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00403"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26535"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26536"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.15"},{"key":"ref22","article-title":"Hybrid ranking network for text-to-SQL","author":"Lyu","year":"2020"},{"key":"ref23","article-title":"GraPPa: Grammar-augmented pre-training for table semantic parsing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3654930"},{"key":"ref25","article-title":"A comprehensive evaluation of ChatGPT\u2019s zero-shot text-to-SQL capability","author":"Liu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref27","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref28","article-title":"C3: Zero-shot text-to-SQL with ChatGPT","author":"Dong","year":"2023"},{"key":"ref29","article-title":"Knapsack optimization-based schema linking for LLM-based text-to-SQL generation","author":"Yuan","year":"2025"},{"key":"ref30","article-title":"Structure guided large language model for SQL generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.562"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1204"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.176"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.142"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.62"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.702"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.105"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1443"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.167"},{"key":"ref42","article-title":"Spider 2.0: Evaluating language models on real-world enterprise text-to-SQL workflows","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lei"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.364"},{"key":"ref44","article-title":"Dr spider: A diagnostic evaluation benchmark towards text-to-SQL robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3653375"},{"key":"ref46","first-page":"41832","article-title":"Coder reviewer reranking for code generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.327"},{"key":"ref48","first-page":"540","article-title":"MAC-SQL: A multi-agent collaborative framework for text-to-SQL","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.641"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00143"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.trl-1.4"},{"key":"ref52","article-title":"PET-SQL: A prompt-enhanced two-stage text-to-SQL framework with cross-consistency","author":"Li","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.324"},{"key":"ref55","first-page":"337","article-title":"MCS-SQL: Leveraging multiple prompts and multiple-choice selection for text-to-SQL generation","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Lee"},{"key":"ref56","article-title":"CHESS: Contextual harnessing for efficient SQL synthesis","author":"Talaei","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682003"},{"key":"ref58","article-title":"The death of schema linking? Text-to-SQL in the age of well-reasoned language models","volume-title":"Proc. 3rd Table Representation Learn. Workshop","author":"Maamari"},{"key":"ref59","article-title":"RSL-SQL: Robust schema linking in text-to-SQL generation","author":"Cao","year":"2024"},{"key":"ref60","first-page":"3794","article-title":"Gen-SQL: Efficient text-to-SQL by bridging natural language question and database schema with pseudo-schema","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Shi"},{"key":"ref61","article-title":"ReFoRCE: A text-to-SQL agent with self-refinement, format restriction, and column exploration","volume-title":"Proc. ICLR VerifAI Workshop","author":"Deng"},{"key":"ref62","article-title":"LinkAlign: Scalable schema linking for real-world large-scale multi-database text-to-SQL","author":"Wang","year":"2025"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7022-3_23"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.996"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8076-5_25"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.944"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.227"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.65"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.653"},{"key":"ref71","article-title":"Dubo-SQL: Diverse retrieval-augmented generation and fine tuning for text-to-SQL","author":"Thorpe","year":"2024"},{"key":"ref72","first-page":"10390","article-title":"In-context reinforcement learning with retrieval-augmented generation for text-to-SQL","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Toteja"},{"key":"ref73","article-title":"SAFE-SQL: Self-augmented in-context learning with fine-grained example selection for text-to-SQL","author":"Lee","year":"2025"},{"key":"ref74","article-title":"SQL-PaLM: Improved large language model adaptation for text-to-SQL","volume":"2024","author":"Sun","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref75","article-title":"SQL-CRAFT: Text-to-SQL through interactive refinement and enhanced reasoning","author":"Xia","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.436"},{"key":"ref77","article-title":"CHASE-SQL: Multi-path reasoning and preference optimized candidate selection in text-to-SQL","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pourreza"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.231"},{"key":"ref79","first-page":"26106","article-title":"LEVER: Learning to verify language-to-code generation with execution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ni"},{"key":"ref80","article-title":"Teaching large language models to self-debug","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref81","article-title":"E-SQL: Direct schema linking via question enrichment in text-to-SQL","author":"Cafero\u011flu","year":"2024"},{"key":"ref82","first-page":"25426","article-title":"CLLMs: Consistency large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kou"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.707"},{"key":"ref84","article-title":"StructLM: Towards building generalist models for structured knowledge grounding","volume-title":"Proc. Conf. Lang. Model.","author":"Zhuang"},{"key":"ref85","article-title":"XiYan-SQL: A multi-generator ensemble framework for text-to-SQL","author":"Gao","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.552"},{"key":"ref87","article-title":"Code Llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.107"},{"key":"ref90","article-title":"ROUTE: Robust multitask tuning and collaboration for text-to-SQL","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qin"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40555-y"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00776-8"},{"key":"ref93","first-page":"2166","article-title":"Recent advances in text-to-SQL: A survey of what we have and what we expect","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Deng"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3400824"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494139"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.51"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1444"},{"key":"ref101","article-title":"SQLNet: Generating structured queries from natural language without reinforcement learning","author":"Xu","year":"2017"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref103","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.350"},{"key":"ref105","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"key":"ref106","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref107","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref108","article-title":"How to prompt LLMs for text-to-SQL: A study in zero-shot, single-domain, and cross-domain settings","volume-title":"Proc. NeurIPS 2nd Table Representation Learn. Workshop","author":"Chang"},{"key":"ref109","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024"},{"key":"ref110","article-title":"Prompt engineering for healthcare: Methodologies and applications","author":"Wang","year":"2023"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101260"},{"key":"ref112","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref114","article-title":"DB-GPT: Empowering database interactions with private large language models","author":"Xue","year":"2024"},{"key":"ref115","article-title":"DBCopilot: Scaling natural language querying to massive databases","author":"Wang","year":"2023"},{"key":"ref116","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref117","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref118","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref119","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref120","article-title":"Benchmarking the text-to-SQL capability of large language models: A comprehensive evaluation","author":"Zhang","year":"2024"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"ref122","first-page":"30378","article-title":"The unreliability of explanations in few-shot prompting for textual reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref123","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref124","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref126","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref127","article-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","volume":"2023","author":"Chen","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref128","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov"},{"key":"ref129","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657961"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298895"},{"key":"ref132","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Erhan"},{"key":"ref133","article-title":"StarCoder: May the source be with you","volume":"2023","author":"Li","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref134","article-title":"Aligning large language models with human: A survey","author":"Wang","year":"2023"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.89"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.620"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.779"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.99"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00837-0"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICMC60390.2024.00008"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref143","article-title":"Rethinking interpretability in the era of large language models","author":"Singh","year":"2024"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"ref145","article-title":"A comprehensive study of knowledge editing for large language models","author":"Zhang","year":"2024"},{"key":"ref146","article-title":"Mass-editing memory in a transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng"},{"key":"ref147","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Meng"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.296"},{"key":"ref149","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.122"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29823"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.569"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11233837\/11160657.pdf?arnumber=11160657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T19:09:42Z","timestamp":1762888182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11160657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":152,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3609486","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}