{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:01:45Z","timestamp":1785355305689,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LMS26F020047"],"award-info":[{"award-number":["LMS26F020047"]}]},{"name":"Zhejiang Provincial Postdoctoral Research Excellence Funding Program","award":["ZJ2025100"],"award-info":[{"award-number":["ZJ2025100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3713477","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:06:14Z","timestamp":1784145974000},"page":"111240-111257","source":"Crossref","is-referenced-by-count":0,"title":["Template-to-Text: Hierarchical Structure-Aware Retrieval for Controllable Document Generation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9887-2731","authenticated-orcid":false,"given":"Yongpan","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8618-429X","authenticated-orcid":false,"given":"Yu","family":"Tan","sequence":"additional","affiliation":[{"name":"Hangzhou Yuyuan Technology Company Ltd.","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-6048","authenticated-orcid":false,"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8780-5546","authenticated-orcid":false,"given":"Yunzhi","family":"Hao","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2025.104330","article-title":"Enhancing retrieval-augmented generation for interoperable industrial knowledge representation and inference toward cognitive digital twins","volume":"171","author":"Shi","year":"2025","journal-title":"Comput. Ind."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3591561"},{"key":"ref4","article-title":"A retrieval-augmented generation framework for academic literature navigation in data science","author":"Aytar","year":"2024","journal-title":"arXiv:2412.15404"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"4534","DOI":"10.1016\/j.procs.2024.09.303","article-title":"Exploring business events using multi-source RAG","volume":"246","author":"Arslan","year":"2024","journal-title":"Proc. Comput. Sci."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3731715.3733451"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00019-5"},{"key":"ref9","first-page":"9481","article-title":"AI-researcher: Autonomous scientific innovation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i47.41489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3617680"},{"key":"ref12","article-title":"A complete survey on generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 all you need?","author":"Zhang","year":"2023","journal-title":"arXiv:2303.11717"},{"key":"ref13","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref14","volume-title":"Introducing GPT-5.2: The Most Advanced Frontier Model for Professional Work and Long-Running Agents","year":"2025"},{"key":"ref15","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-025-00335-5"},{"key":"ref17","first-page":"865","article-title":"LongGenBench: Long-context generation benchmark","volume-title":"Proc. Findings Assoc. Comput. Linguistics: EMNLP","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3655"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.859"},{"key":"ref21","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref22","first-page":"16967","article-title":"EventRAG: Enhancing LLM generation with event knowledge graphs","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Yang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2024.01.001"},{"key":"ref24","first-page":"27022","article-title":"SeaKR: Self-aware knowledge retrieval for adaptive retrieval augmented generation","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Yao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.acl-long.189"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2024.101687","article-title":"Seq2Seq dynamic planning network for progressive text generation","volume":"89","author":"Wu","year":"2025","journal-title":"Comput. Speech Lang."},{"key":"ref27","article-title":"Pretrained transformers as universal computation engines","author":"Lu","year":"2021","journal-title":"arXiv:2103.05247"},{"key":"ref28","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019","journal-title":"arXiv:1909.05858"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"issue":"1","key":"ref30","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref32","first-page":"2253","article-title":"Challenges in data-to-document generation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wiseman"},{"key":"ref33","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017378"},{"key":"ref35","first-page":"889","article-title":"Hierarchical neural story generation","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Fan"},{"key":"ref36","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref37","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref38","article-title":"Plug and play language models: A simple approach to controlled text generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dathathri"},{"key":"ref39","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref40","article-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv:2210.03629"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3906\/elk-2105-242"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.35378\/gujs.710730"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.02.106"},{"key":"ref44","first-page":"2463","article-title":"Language models as knowledge bases?","volume-title":"Proc. 9th Int. Joint Conf. Natural Lang. Process. Conf. Empirical Methods Natural Lang. Process (EMNLP-IJCNLP)","author":"Petroni"},{"key":"ref45","article-title":"The pile: An 800GB dataset of diverse text for language modeling","author":"Gao","year":"2021","journal-title":"arXiv:2101.00027"},{"key":"ref46","first-page":"32001","article-title":"RAG+: Enhancing retrieval-augmented generation with application-aware reasoning","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wang"},{"key":"ref47","article-title":"REALM: Retrieval-augmented language model pre-training","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref48","first-page":"6769","article-title":"Dense passage retrieval for open-domain question answering","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Karpukhin"},{"key":"ref49","first-page":"157","article-title":"Lost in the middle: How language models use long contexts","volume-title":"Proc. Trans. Assoc. Comput. Linguistics","volume":"12","author":"Liu"},{"key":"ref50","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref51","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref52","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Press"},{"key":"ref53","article-title":"Advanced rag techniques: An illustrated overview","author":"Ilin","year":"2023","journal-title":"Medium"},{"key":"ref54","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2020"},{"key":"ref55","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref56","first-page":"7881","article-title":"BLEURT: Learning robust metrics for text generation","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Sellam"},{"key":"ref57","article-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020","journal-title":"arXiv:2006.14799"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.55"},{"key":"ref59","first-page":"1051","article-title":"Large language models can self-improve","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Huang"},{"key":"ref60","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv:2205.10625"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1239"},{"key":"ref62","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref63","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Lin"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11611160.pdf?arnumber=11611160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T19:14:26Z","timestamp":1785352466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11611160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3713477","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}