{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T07:30:13Z","timestamp":1774164613292,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3569872","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T17:33:25Z","timestamp":1747244005000},"page":"85072-85083","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing RAG Performance by Representing Hierarchical Nodes in Headers for Tabular Data"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-0312","authenticated-orcid":false,"given":"Minchae","family":"Song","sequence":"first","affiliation":[{"name":"NongHyup Financial Research Institution, NongHyup Financial Group, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Retrieval-augmented generation for AI-generated content: A survey","author":"Zhao","year":"2024","journal-title":"arXiv:2402.19473"},{"key":"ref2","first-page":"1","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wei"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"ref4","article-title":"RealTime QA: What\u2019s the answer right now?","author":"Kasai","year":"2022","journal-title":"arXiv:2207.13332"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3513155"},{"key":"ref6","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref7","first-page":"1","article-title":"THoRR: Complex table retrieval and refinement for RAG","volume-title":"Proc. Workshop Inf. Retrieval\u2019s Role RAG Syst. (IR-RAG)","author":"Kim"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3518205"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"ref10","article-title":"Extracting training data from large language models","author":"Carlini"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.88"},{"key":"ref12","article-title":"Enhancing large language model performance to answer questions and extract information more accurately","author":"Zhang","year":"2024","journal-title":"arXiv:2402.01722"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3508747"},{"key":"ref14","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref15","article-title":"Novel preprocessing technique for data embedding in engineering code generation using large language model","author":"Lin","year":"2023","journal-title":"arXiv:2311.16267"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671975"},{"key":"ref17","first-page":"5549","article-title":"TabLLM: Few-shot classification of tabular data with large language models","volume-title":"Proc. AISTATS","author":"Hegselmann"},{"key":"ref18","first-page":"1","article-title":"TransTab: Learning transferable tabular transformers across tables","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref19","first-page":"1","article-title":"LIFT: Language-interfaced fine-tuning for non-language machine learning tasks","volume-title":"Proc. NeurIPS","author":"Dinh"},{"key":"ref20","first-page":"1","article-title":"TabPFN: A transformer that solves small tabular classification problems in a second","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hollmann"},{"key":"ref21","article-title":"Transformers can do Bayesian inference","author":"M\u00fcller","year":"2021","journal-title":"arXiv:2112.10510"},{"key":"ref22","article-title":"TableLlama: Towards open large generalist models for tables","author":"Zhang","year":"2023","journal-title":"arXiv:2311.09206"},{"key":"ref23","first-page":"1","article-title":"UniTabE: A universal pretraining protocol for tabular foundation model in data science","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.24"},{"key":"ref26","article-title":"End-to-end table question answering via retrieval-augmented generation","author":"Pan","year":"2022","journal-title":"arXiv:2203.16714"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.68"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/629"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlp4convai-1.6"},{"key":"ref32","article-title":"ERATTA: Extreme RAG for table to answers with large language models","author":"Roychowdhury","year":"2024","journal-title":"arXiv:2405.03963"},{"key":"ref33","article-title":"Linearly multiplexed photon number resolving single-photon detectors array","author":"Limongi","year":"2024","journal-title":"arXiv:2408.12345"},{"key":"ref34","article-title":"TableGPT: Towards unifying tables, nature language and commands into one GPT","author":"Zha","year":"2023","journal-title":"arXiv:2307.08674"},{"key":"ref35","article-title":"Open-domain question answering","author":"Greenwood","year":"2005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MedAI62885.2024.00051"},{"key":"ref38","article-title":"Retrieval-augmented test generation: How far are we?","author":"Shin","year":"2024","journal-title":"arXiv:2409.12682"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/app14177782"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/I-SMAC61858.2024.10714814"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00258"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698671"},{"key":"ref44","article-title":"Pseudo-knowledge graph: Meta-path guided retrieval and in-graph text for RAG-equipped LLM","author":"Yang","year":"2025","journal-title":"arXiv:2503.00309"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11003975.pdf?arnumber=11003975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T05:07:27Z","timestamp":1747804047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11003975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3569872","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}