{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T20:15:44Z","timestamp":1785528944776,"version":"3.56.0"},"reference-count":63,"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"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & communications Technology Planning & Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Government (MSIT)"},{"name":"IITP (Institute of Information & Communications Technology Planning & Evaluation)-ITRC"},{"name":"Korea Government [Ministry of Science and Information and Communication Technology (ICT)]","award":["IITP-2025-RS-2021-II211835"],"award-info":[{"award-number":["IITP-2025-RS-2021-II211835"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3542125","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T18:32:06Z","timestamp":1739557926000},"page":"36978-36994","source":"Crossref","is-referenced-by-count":19,"title":["Legal Query RAG"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6092-3962","authenticated-orcid":false,"given":"Rahman S. M.","family":"Wahidur","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8832-3161","authenticated-orcid":false,"given":"Sumin","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8099-4505","authenticated-orcid":false,"given":"Haeung","family":"Choi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7314-9517","authenticated-orcid":false,"given":"David S.","family":"Bhatti","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8528-5778","authenticated-orcid":false,"given":"Heung-No","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TLT.2024.3456128"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-024-02120-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00873-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.09.002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2023.0254"},{"key":"ref6","article-title":"Lawyer LLaMA technical report","volume-title":"arXiv:2305.15062","author":"Huang","year":"2023"},{"key":"ref7","article-title":"Hallucination-free? Assessing the reliability of leading AI legal research tools","author":"Magesh","year":"2024","journal-title":"arXiv:2405.20362"},{"key":"ref8","article-title":"Here\u2019s what happens when your lawyer uses ChatGPT","author":"Benjamin","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/jla\/laae003"},{"key":"ref10","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"ref12","first-page":"1","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Asai"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3415470"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3350638"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"ref17","volume-title":"Exploring Advanced RAG Techniques for AI","author":"Sharma","year":"2024"},{"key":"ref18","volume-title":"Advanced RAG Techniques: An Illustrated Overview","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"ref20","first-page":"1","article-title":"Generate rather than retrieve: Large language models are strong context generators","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref21","volume-title":"HanFei-1.0","author":"Wen","year":"2023"},{"key":"ref22","volume-title":"Chinese Law Large Language Model","author":"Liu","year":"2023"},{"key":"ref23","article-title":"A brief report on LawGPT 1.0: A virtual legal assistant based on GPT-3","volume-title":"arXiv:2302.05729","author":"Nguyen","year":"2023"},{"key":"ref24","volume-title":"LexiLaw","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000568"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300068"},{"key":"ref27","article-title":"DISC-LawLLM: Fine-tuning large language models for intelligent legal services","author":"Yue","year":"2023","journal-title":"arXiv:2309.11325"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63646-2_29"},{"key":"ref29","first-page":"10448","article-title":"LexDrafter: Terminology drafting for legislative documents using retrieval augmented generation","volume-title":"Proc. Int. Conf. Comput. Linguistics, Lang. Resour. Eval. (LREC-COLING)","author":"Chouhan"},{"key":"ref30","first-page":"346","article-title":"KAB: Knowledge augmented BERT2BERT automated questions-answering system for jurisprudential legal opinions","volume":"22","author":"Alotaibi","year":"2022","journal-title":"Int. J. Comput. Sci. Netw. Security, IJCSNS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE52691.2021.00011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1031171.1031181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref34","article-title":"Efficient natural language response suggestion for smart reply","author":"Henderson","year":"2017","journal-title":"arXiv:1705.00652"},{"key":"ref35","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref36","volume-title":"The Faiss Library","author":"Douze","year":"2024"},{"key":"ref37","article-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv:2210.03629"},{"key":"ref38","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref39","volume-title":"QA Legal Dataset Train","author":"Bunescu","year":"2023"},{"key":"ref40","volume-title":"Stanford Alpaca: An Instruction-following LLaMA Model","author":"Rohan","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref43","first-page":"119","article-title":"Parameter-efficient legal domain adaptation","volume-title":"Proc. Natural Legal Lang. Process. Workshop","author":"Li"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4583531"},{"key":"ref46","first-page":"1","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref49","article-title":"Retrieve anything to augment large language models","author":"Zhang","year":"2023","journal-title":"arXiv:2310.07554"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref51","article-title":"GISTEmbed: Guided in-sample selection of training negatives for text embedding fine-tuning","author":"Solatorio","year":"2024","journal-title":"arXiv:2402.16829"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref53","volume-title":"Llama 3 Model Card","year":"2024"},{"key":"ref54","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/AIAM48774.2019.00015"},{"key":"ref56","article-title":"Evaluation of RAG metrics for question answering in the telecom domain","author":"Roychowdhury","year":"2024","journal-title":"arXiv:2407.12873"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.02.024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.100"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref60","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref61","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref62","first-page":"30318","article-title":"Gpt3. Int8 (): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dettmers"},{"key":"ref63","volume-title":"TRL: Transformer Reinforcement Learning","author":"Leandro","year":"2020"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10887211.pdf?arnumber=10887211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T06:15:01Z","timestamp":1741068901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3542125","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}