{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:28:29Z","timestamp":1790184509552,"version":"4.1.0"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMOD Rec."],"published-print":{"date-parts":[[2026,1,19]]},"abstract":"<jats:p>Large language models (LLMs) enable the state-ofthe- art in language processing by framing diverse tasks- from code synthesis and healthcare to finance, digital assistance, and scientific discovery-as next-token prediction problems [38, 53, 60, 65, 72, 20, 68, 76, 32]. In addition, LLMs enable automation in data science and engineering, optimizing processes such as data analysis, manipulation, querying, interpretation, research, and education [33, 7, 8, 22, 24, 42, 77, 37, 43, 44, 66, 49].<\/jats:p>\n                  <jats:p>LLMs encode probabilistic token patterns instead of maintaining explicit knowledge structures, which (1) constrains multi-step reasoning under the next-token prediction paradigm; (2) ties outputs to static, pre-cutoff training data-undermining performance on evolving knowledge tasks; and (3) lacks a built-in factual verification mechanism, resulting in hallucinations [25].<\/jats:p>","DOI":"10.1145\/3793217.3793229","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T23:18:37Z","timestamp":1768951117000},"page":"33-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Retrieval-augmented Generation (RAG): What is There for Data Management Researchers? A discussion on research from a panel at LLM+Vector Data Workshop @ IEEE ICDE 2025"],"prefix":"10.1145","volume":"54","author":[{"given":"Arijit","family":"Khan","sequence":"first","affiliation":[{"name":"AAU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyu","family":"Luo","sequence":"additional","affiliation":[{"name":"HKUST (GZ)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"UNSW"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofang","family":"Zhou","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"DIAL@HKUST(GZ) DeepFund Project https:\/\/github.com\/HKUSTDial\/DeepFund"},{"key":"e_1_2_1_2_1","unstructured":"DIAL@HKUST(GZ) https:\/\/github.com\/HKUSTDial"},{"key":"e_1_2_1_3_1","unstructured":"DIAL@HKUST(GZ) OpenManus Project https: \/\/github.com\/FoundationAgents\/OpenManus"},{"key":"e_1_2_1_4_1","unstructured":"DIAL@HKUST(GZ) Text-to-SQL Project https: \/\/github.com\/HKUSTDial\/NL2SQL_Handbook"},{"key":"e_1_2_1_5_1","volume-title":"ICDE 2026, Second International Workshop on Coupling of Large Language Models with Vector Data Management: Agentic RAG Edition, https:\/\/llmvdb2.github.io\/","author":"Vector LLM","unstructured":"LLM + Vector Data @ ICDE 2026, Second International Workshop on Coupling of Large Language Models with Vector Data Management: Agentic RAG Edition, https:\/\/llmvdb2.github.io\/"},{"key":"e_1_2_1_6_1","volume-title":"https:\/\/learn.microsoft.com\/enus\/ azure\/search\/retrieval-augmentedgeneration- overview?tabs=docs","author":"Retrieval","year":"2025","unstructured":"Retrieval augmented generation (rag) in azure ai search. https:\/\/learn.microsoft.com\/enus\/ azure\/search\/retrieval-augmentedgeneration- overview?tabs=docs, 2025."},{"key":"e_1_2_1_7_1","first-page":"962","volume-title":"International Conference on Extending Database Technology (EDBT)","author":"Amer-Yahia S.","year":"2025","unstructured":"S. Amer-Yahia, J. Bogojeska, R. Facchinetti, V. Franceschi, A. Gionis, K. Hose, G. Koutrika, R. Kouyos, M. Lissandrini, S. Maniu, K. Mirylenka, D. Mottin, T. Palpanas, M. Rigotti, and Y. Velegrakis. Towards reliable conversational data analytics. In International Conference on Extending Database Technology (EDBT), pages 962--969, 2025."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631504.3631518"},{"key":"e_1_2_1_9_1","volume-title":"Managing vector data for retrieval augmented generation: Systems and algorithms (Dagstuhl Seminar 26161). https:\/\/www.dagstuhl.de\/en\/seminars\/ seminar-calendar\/seminar-details\/26161","author":"Amer-Yahia S.","year":"2026","unstructured":"S. Amer-Yahia, A. Khan, W. Lehner, S. Mehrotra, and W. Zhang. Managing vector data for retrieval augmented generation: Systems and algorithms (Dagstuhl Seminar 26161). https:\/\/www.dagstuhl.de\/en\/seminars\/ seminar-calendar\/seminar-details\/26161, 2026."},{"key":"e_1_2_1_10_1","volume-title":"Text2SQL is not enough: Unifying AI and databases with TAG. CoRR, abs\/2408.14717","author":"Biswal A.","year":"2024","unstructured":"A. Biswal, L. Patel, S. Jha, A. Kamsetty, S. Liu, J. E. Gonzalez, C. Guestrin, and M. Zaharia. Text2SQL is not enough: Unifying AI and databases with TAG. CoRR, abs\/2408.14717, 2024."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3716376"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589302"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3523210.3523223"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589406"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3148237"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709663"},{"issue":"4","key":"e_1_2_1_18_1","first-page":"71","article-title":"RAG-based question answering over heterogeneous data and text","volume":"48","author":"Christmann P.","year":"2024","unstructured":"P. Christmann and G. Weikum. RAG-based question answering over heterogeneous data and text. IEEE Data Eng. Bull., 48(4):71--86, 2024.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635738"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"e_1_2_1_21_1","volume-title":"From local to global: A graph RAG approach to query-focused summarization. CoRR, abs\/2404.16130","author":"Edge D.","year":"2024","unstructured":"D. Edge, H. Trinh, N. Cheng, J. Bradley, A. Chao, A. Mody, S. Truitt, and J. Larson. From local to global: A graph RAG approach to query-focused summarization. CoRR, abs\/2404.16130, 2024."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611527"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375395.3387641"},{"key":"e_1_2_1_24_1","volume-title":"Proc. VLDB","author":"Halevy A. Y.","unstructured":"A. Y. Halevy, Y. Choi, A. Floratou, M. J. Franklin, N. F. Noy, and H. Wang. Will llms reshape, supercharge, or kill data science? Proc. VLDB"},{"key":"e_1_2_1_25_1","volume-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. 43(2)","author":"Huang L.","year":"2025","unstructured":"L. Huang, W. Yu, W. Ma, W. Zhong, Z. Feng, H. Wang, Q. Chen, W. Peng, X. Feng, B. Qin, and T. Liu. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. 43(2), 2025."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_2_1_27_1","volume-title":"Workshops at the International Conference on Data Engineering (ICDEW)","author":"Khan A.","year":"2025","unstructured":"A. Khan, Y. Wang, W. Zhang, Y. Tian, and M. T. \u00d6zsu. LLM + vector data: Coupling of large language models with vector data management for enhancing data science. In Workshops at the International Conference on Data Engineering (ICDEW), 2025."},{"key":"e_1_2_1_28_1","volume-title":"Gemini 1.5 Pro 2M context window, code execution capabilities, and Gemma 2 are available today. https:\/\/developers.googleblog.com\/ en\/new-features-for-the-gemini-apiand- google-ai-studio\/","author":"Kilpatrick L.","year":"2024","unstructured":"L. Kilpatrick, S. B. Mallick, and R. Kofman. Gemini 1.5 Pro 2M context window, code execution capabilities, and Gemma 2 are available today. https:\/\/developers.googleblog.com\/ en\/new-features-for-the-gemini-apiand- google-ai-studio\/, 2024."},{"key":"e_1_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Lewis P.","year":"2020","unstructured":"P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. K\u00fcttler, M. Lewis, W. Yih, T. Rockt\u00e4schel, S. Riedel, and D. Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems (NeurIPS), 2020."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682003"},{"key":"e_1_2_1_31_1","volume-title":"Forty-Second International Conference on Machine Learning, ICML 2025","author":"Li B.","year":"2025","unstructured":"B. Li, J. Zhang, J. Fan, Y. Xu, C. Chen, N. Tang, and Y. Luo. Alpha-sql: Zero-shot text-to-sql using monte carlo tree search. In Forty-Second International Conference on Machine Learning, ICML 2025, Vancouver, Canada, July 13--19, 2025. OpenReview.net, 2025."},{"key":"e_1_2_1_32_1","volume-title":"Deepfund: Will LLM be professional at fund investment? A live arena perspective. CoRR, abs\/2503.18313","author":"Li C.","year":"2025","unstructured":"C. Li, Y. Shi, Y. Luo, and N. Tang. Deepfund: Will LLM be professional at fund investment? A live arena perspective. CoRR, abs\/2503.18313, 2025."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685838"},{"key":"e_1_2_1_34_1","volume-title":"A survey on large language model acceleration based on kv cache management","author":"Li H.","year":"2025","unstructured":"H. Li, Y. Li, A. Tian, T. Tang, Z. Xu, X. Chen, N. Hu, W. Dong, Q. Li, and L. Chen. A survey on large language model acceleration based on kv cache management, 2025."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715240"},{"key":"e_1_2_1_36_1","volume-title":"Musings about the future of search: A return to the past? CoRR, abs\/2412.18956","author":"Lin J.","year":"2024","unstructured":"J. Lin, P. Gupta, W. Horn, and G. Mishne. Musings about the future of search: A return to the past? CoRR, abs\/2412.18956, 2024."},{"key":"e_1_2_1_37_1","volume-title":"LEAD: iterative data selection for efficient LLM instruction tuning. CoRR, abs\/2505.07437","author":"Lin X.","year":"2025","unstructured":"X. Lin, Y. Qi, Y. Zhu, T. Palpanas, C. Chai, N. Tang, and Y. Luo. LEAD: iterative data selection for efficient LLM instruction tuning. CoRR, abs\/2505.07437, 2025."},{"key":"e_1_2_1_38_1","volume-title":"Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. CoRR, abs\/2504.01990","author":"Liu B.","year":"2025","unstructured":"B. Liu, X. Li, J. Zhang, J. Wang, T. He, S. Hong, H. Liu, S. Zhang, K. Song, K. Zhu, Y. Cheng, S. Wang, X. Wang, Y. Luo, H. Jin, P. Zhang, O. Liu, J. Chen, H. Zhang, Z. Yu, H. Shi, B. Li, D. Wu, F. Teng, X. Jia, J. Xu, J. Xiang, Y. Lin, T. Liu, T. Liu, Y. Su, H. Sun, G. Berseth, J. Nie, I. Foster, L. T. Ward, Q. Wu, Y. Gu, M. Zhuge, X. Tang, H. Wang, J. You, C. Wang, J. Pei, Q. Yang, X. Qi, and C. Wu. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. CoRR, abs\/2504.01990, 2025."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00317"},{"key":"e_1_2_1_40_1","volume-title":"A survey of text-to-sql in the era of llms: Where are we, and where are we going?","author":"Liu X.","year":"2025","unstructured":"X. Liu, S. Shen, B. Li, P. Ma, R. Jiang, Y. Zhang, J. Fan, G. Li, N. Tang, and Y. Luo. A survey of text-to-sql in the era of llms: Where are we, and where are we going?, 2025."},{"key":"e_1_2_1_41_1","volume-title":"Nl2sql-bugs: A benchmark for detecting semantic errors in NL2SQL translation. CoRR, abs\/2503.11984","author":"Liu X.","year":"2025","unstructured":"X. Liu, S. Shen, B. Li, N. Tang, and Y. Luo. Nl2sql-bugs: A benchmark for detecting semantic errors in NL2SQL translation. CoRR, abs\/2503.11984, 2025."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00019"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457261"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114848"},{"key":"e_1_2_1_45_1","volume-title":"How we built Text-to-SQL at Pinterest. https:\/\/medium.com\/pinterestengineering\/ how-we-built-text-to-sqlat- pinterest-30bad30dabff","author":"Obeng A.","year":"2024","unstructured":"A. Obeng, J. Zhong, and C. Gu. How we built Text-to-SQL at Pinterest. https:\/\/medium.com\/pinterestengineering\/ how-we-built-text-to-sqlat- pinterest-30bad30dabff, 2024."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00864-x"},{"key":"e_1_2_1_47_1","volume-title":"LOTUS: enabling semantic queries with llms over tables of unstructured and structured data. CoRR, abs\/2407.11418","author":"Patel L.","year":"2024","unstructured":"L. Patel, S. Jha, C. Guestrin, and M. Zaharia. LOTUS: enabling semantic queries with llms over tables of unstructured and structured data. CoRR, abs\/2407.11418, 2024."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722449.3722463"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-019-00588-3"},{"key":"e_1_2_1_50_1","volume-title":"Data playwright: Authoring data videos with annotated narration. CoRR, abs\/2410.03093","author":"Shen L.","year":"2024","unstructured":"L. Shen, H. Li, Y. Wang, T. Luo, Y. Luo, and H. Qu. Data playwright: Authoring data videos with annotated narration. CoRR, abs\/2410.03093, 2024."},{"key":"e_1_2_1_51_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shim J.","year":"2025","unstructured":"J. Shim, G. Seo, C. Lim, and Y. Jo. Tooldial: Multi-turn dialogue generation method for tool-augmented language models. In International Conference on Learning Representations (ICLR), 2025."},{"key":"e_1_2_1_52_1","volume-title":"Agentic retrieval-augmented generation: A survey on agentic RAG. CoRR, abs\/2501.09136","author":"Singh A.","year":"2025","unstructured":"A. Singh, A. Ehtesham, S. Kumar, and T. T. Khoei. Agentic retrieval-augmented generation: A survey on agentic RAG. CoRR, abs\/2501.09136, 2025."},{"key":"e_1_2_1_53_1","volume-title":"Large language models encode clinical knowledge. Nature, 620(7972)","author":"Singhal K.","year":"2023","unstructured":"K. Singhal, S. Azizi, T. Tu, S. S. Mahdavi, J. Wei, H. W. Chung, N. Scales, A. Tanwani, H. Cole-Lewis, S. Pfohl, et al. Large language models encode clinical knowledge. Nature, 620(7972), 2023."},{"key":"e_1_2_1_54_1","volume-title":"PROCEEDINGS OF THE ACM ON WEB CONFERENCE 2025","author":"X. TAN, X. WANG, Q. LIU, X. XU, X.","year":"2025","unstructured":"X. TAN, X. WANG, Q. LIU, X. XU, X. YUAN, and W. ZHANG. Paths-over-graph: Knowledge graph empowered large language model reasoning. In PROCEEDINGS OF THE ACM ON WEB CONFERENCE 2025, 2025."},{"key":"e_1_2_1_55_1","volume-title":"ZHANG. Hydra: Structured cross-source enhanced large language model reasoning. ARXIV PREPRINT ARXIV:2505.17464","author":"X. TAN, X. WANG, Q. LIU, X. XU, X. YUAN, L.","year":"2025","unstructured":"X. TAN, X. WANG, Q. LIU, X. XU, X. YUAN, L. ZHU, and W. ZHANG. Hydra: Structured cross-source enhanced large language model reasoning. ARXIV PREPRINT ARXIV:2505.17464, 2025."},{"key":"e_1_2_1_56_1","volume-title":"CIDR. www.cidrdb.org","author":"Tang N.","year":"2024","unstructured":"N. Tang, C. Yang, J. Fan, L. Cao, Y. Luo, and A. Y. Halevy. Verifai: Verified generative AI. In CIDR. www.cidrdb.org, 2024."},{"issue":"4","key":"e_1_2_1_57_1","first-page":"135","article-title":"Symphony: Towards trustworthy question answering and verification using RAG over multimodal data lakes","volume":"48","author":"Tang N.","year":"2024","unstructured":"N. Tang, C. Yang, Z. Zhang, Y. Luo, J. Fan, L. Cao, S. Madden, and A. Y. Halevy. Symphony: Towards trustworthy question answering and verification using RAG over multimodal data lakes. IEEE Data Eng. Bull., 48(4):135--146, 2024.","journal-title":"IEEE Data Eng. Bull."},{"issue":"3","key":"e_1_2_1_58_1","first-page":"39","article-title":"Approximate nearest neighbor search in high dimensional vector databases: Current research and future directions","volume":"47","author":"Tian Y.","year":"2023","unstructured":"Y. Tian, Z. Yue, R. Zhang, X. Zhao, B. Zheng, and X. Zhou. Approximate nearest neighbor search in high dimensional vector databases: Current research and future directions. IEEE Data Eng. Bull., 47(3):39--54, 2023.","journal-title":"IEEE Data Eng. Bull."},{"issue":"1","key":"e_1_2_1_59_1","first-page":"57","article-title":"idatalake: An llm-powered analytics system on data lakes","volume":"49","author":"Wang J.","year":"2025","unstructured":"J. Wang, G. Li, and J. Feng. idatalake: An llm-powered analytics system on data lakes. IEEE Data Eng. Bull., 49(1):57--69, 2025.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_2_1_60_1","volume-title":"NeurIPS Workshop on Instruction Tuning and Instruction Following","author":"Wang N.","year":"2023","unstructured":"N. Wang, H. Yang, and C. D. Wang. FinGPT: Instruction tuning benchmark for open-source large language models in financial datasets. NeurIPS Workshop on Instruction Tuning and Instruction Following, 2023."},{"key":"e_1_2_1_61_1","volume-title":"Transxssm: A hybrid transformer state space model with unified rotary position embedding. CoRR, abs\/2506.09507","author":"Wu B.","year":"2025","unstructured":"B. Wu, J. Shi, Y. Wu, N. Tang, and Y. Luo. Transxssm: A hybrid transformer state space model with unified rotary position embedding. CoRR, abs\/2506.09507, 2025."},{"key":"e_1_2_1_62_1","volume-title":"Transxssm: A hybrid transformer state space model with unified rotary position embedding","author":"Wu B.","year":"2025","unstructured":"B. Wu, J. Shi, Y. Wu, N. Tang, and Y. Luo. Transxssm: A hybrid transformer state space model with unified rotary position embedding, 2025."},{"key":"e_1_2_1_63_1","volume-title":"Concise reasoning, big gains: Pruning long reasoning trace with difficulty-aware prompting","author":"Wu Y.","year":"2025","unstructured":"Y. Wu, J. Shi, B. Wu, J. Zhang, X. Lin, N. Tang, and Y. Luo. Concise reasoning, big gains: Pruning long reasoning trace with difficulty-aware prompting, 2025."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.003"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681992"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661370"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.296"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.04.003"},{"key":"e_1_2_1_70_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yue Z.","year":"2025","unstructured":"Z. Yue, H. Zhuang, A. Bai, K. Hui, R. Jagerman, H. Zeng, Z. Qin, D. Wang, X. Wang, and M. Bendersky. Inference scaling for long-context retrieval augmented generation. In International Conference on Learning Representations (ICLR), 2025."},{"key":"e_1_2_1_71_1","volume-title":"ICLR. OpenReview.net","author":"Zhang J.","year":"2025","unstructured":"J. Zhang, J. Xiang, Z. Yu, F. Teng, X. Chen, J. Chen, M. Zhuge, X. Cheng, S. Hong, J. Wang, B. Zheng, B. Liu, Y. Luo, and C. Wu. Aflow: Automating agentic workflow generation. In ICLR. OpenReview.net, 2025."},{"key":"e_1_2_1_72_1","volume-title":"Transactions on Machine Learning Research","author":"Zhang Z.","year":"2024","unstructured":"Z. Zhang, C. Chen, B. Liu, C. Liao, Z. Gong, H. Yu, J. Li, and R. Wang. Unifying the perspectives of NLP and software engineering: A survey on language models for code. Transactions on Machine Learning Research, 2024."},{"key":"e_1_2_1_73_1","volume-title":"Datamosaic: Explainable and verifiable multi-modal data analytics through extract-reason-verify. CoRR, abs\/2504.10036","author":"Zhang Z.","year":"2025","unstructured":"Z. Zhang, Z. Liang, Y. Wu, T. Lin, Y. Luo, and N. Tang. Datamosaic: Explainable and verifiable multi-modal data analytics through extract-reason-verify. CoRR, abs\/2504.10036, 2025."},{"key":"e_1_2_1_74_1","volume-title":"Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473","author":"Zhao P.","year":"2024","unstructured":"P. Zhao, H. Zhang, Q. Yu, Z. Wang, Y. Geng, F. Fu, L. Yang, W. Zhang, and B. Cui. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473, 2024."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.14778\/3594512.3594527"},{"key":"e_1_2_1_76_1","volume-title":"From automation to autonomy: A survey on large language models in scientific discovery. arXiv preprint arXiv:2505.13259","author":"Zheng T.","year":"2025","unstructured":"T. Zheng, Z. Deng, H. T. Tsang, W. Wang, J. Bai, Z. Wang, and Y. Song. From automation to autonomy: A survey on large language models in scientific discovery. arXiv preprint arXiv:2505.13259, 2025."},{"key":"e_1_2_1_77_1","volume-title":"NeurIPS","author":"Zhu Y.","year":"2024","unstructured":"Y. Zhu, S. Du, B. Li, Y. Luo, and N. Tang. Are large language models good statisticians? In NeurIPS, 2024."},{"key":"e_1_2_1_78_1","volume-title":"COLM","author":"Zhu Y.","year":"2025","unstructured":"Y. Zhu, R. Jiang, B. Li, N. Tang, and Y. Luo. Elliesql: Cost-efficient text-to-sql with complexity-aware routing. COLM, 2025"}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793217.3793229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T05:18:13Z","timestamp":1769318293000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793217.3793229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":78,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,1,19]]}},"alternative-id":["10.1145\/3793217.3793229"],"URL":"https:\/\/doi.org\/10.1145\/3793217.3793229","relation":{},"ISSN":["0163-5808"],"issn-type":[{"value":"0163-5808","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"2026-01-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}