{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T02:49:10Z","timestamp":1783392550358,"version":"3.54.6"},"reference-count":68,"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":[{"name":"Universidad Internacional del Ecuador through the Inteligencia Artificial para un Archipi\u00e9lago Protegido: Innovaci\u00f3n en ABG Gal\u00e1pagos","award":["UIDE-GI-PPI-PRY-CI-24-04"],"award-info":[{"award-number":["UIDE-GI-PPI-PRY-CI-24-04"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3622138","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:38:44Z","timestamp":1760636324000},"page":"179759-179775","source":"Crossref","is-referenced-by-count":2,"title":["Legal AI for All: Reducing Perplexity and Boosting Accuracy in Normative Texts With Fine-Tuned LLMs and RAG"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4113-8400","authenticated-orcid":false,"given":"Patricio","family":"Santiago Garc\u00eda-Montero","sequence":"first","affiliation":[{"name":"School of Mathematical and Computational Sciences, Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), Yachay Tech University, Urcuqui, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9575-3539","authenticated-orcid":false,"given":"Paulina","family":"Vizca\u00edno","sequence":"additional","affiliation":[{"name":"Facultad de Ingenierías Digitales y Tecnologías Emergentes, Universidad Internacional del Ecuador (UIDE), Quito, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2731-5531","authenticated-orcid":false,"given":"Iv\u00e1n","family":"Galo Reyes-Chac\u00f3n","sequence":"additional","affiliation":[{"name":"Facultad de Ingenierías Digitales y Tecnologías Emergentes, Universidad Internacional del Ecuador (UIDE), Quito, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4705-7923","authenticated-orcid":false,"given":"Manuel","family":"Eugenio Morocho-Cayamcela","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), Yachay Tech University, Urcuqui, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13370"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5220\/0012763000003753"},{"key":"ref5","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023","journal-title":"Authorea Preprints"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3934\/math.2024963"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3365742"},{"key":"ref8","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref9","volume-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref10","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv:2403.05530"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref12","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv:2408.00118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3991\/ijet.v18i20.42979"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00896-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4347630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-024-00108-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2023.0254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/1121842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3473582"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5220\/0010894000003116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3190408"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.09.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14296\/deeslr.v20i.5610"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659048"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.32719\/26312484.2021.36.5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1344\/der.2020.37.130-153"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.62574\/rmpi.v4iDerecho.128"},{"key":"ref29","volume-title":"Ley Orgnica De Proteccin De Datos Personales","year":"2021"},{"key":"ref30","volume-title":"Reglamento De La Ley Orgnica De Proteccin De Datos Personales","year":"2023"},{"key":"ref31","article-title":"A short survey of viewing large language models in legal aspect","author":"Sun","year":"2023","journal-title":"arXiv:2303.09136"},{"key":"ref32","article-title":"Explaining legal concepts with augmented large language models (GPT-4)","author":"Savelka","year":"2023","journal-title":"arXiv:2306.09525"},{"key":"ref33","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref34","article-title":"Legal summarisation through LLMs: The PRODIGIT project","author":"Dal Pont","year":"2023","journal-title":"arXiv:2308.04416"},{"key":"ref35","article-title":"SaulLM-7B: A pioneering large language model for law","author":"Colombo","year":"2024","journal-title":"arXiv:2403.03883"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-024-01891-1"},{"key":"ref37","article-title":"Zephyr: Direct distillation of LM alignment","author":"Tunstall","year":"2023","journal-title":"arXiv:2310.16944"},{"key":"ref38","article-title":"Towards a theoretical understanding of synthetic data in LLM post-training: A reverse-bottleneck perspective","author":"Gan","year":"2024","journal-title":"arXiv:2410.01720"},{"key":"ref39","article-title":"Code less, align more: Efficient LLM fine-tuning for code generation with data pruning","author":"Tsai","year":"2024","journal-title":"arXiv:2407.05040"},{"key":"ref40","article-title":"From artificial needles to real haystacks: Improving retrieval capabilities in LLMs by finetuning on synthetic data","author":"Xiong","year":"2024","journal-title":"arXiv:2406.19292"},{"key":"ref41","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref42","article-title":"Chatbot arena: An open platform for evaluating LLMs by human preference","author":"Chiang","year":"2024","journal-title":"arXiv:2403.04132"},{"key":"ref43","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref44","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":"ref45","article-title":"How abilities in large language models are affected by supervised fine-tuning data composition","author":"Dong","year":"2023","journal-title":"arXiv:2310.05492"},{"key":"ref46","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv:2204.05862"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.726"},{"key":"ref49","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dettmers"},{"key":"ref50","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref51","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov"},{"key":"ref52","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewis"},{"key":"ref53","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref54","article-title":"FACTS about building retrieval augmented generation-based chatbots","author":"Akkiraju","year":"2024","journal-title":"arXiv:2407.07858"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3486250"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.799"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3624725"},{"key":"ref60","volume-title":"Preguntas Y Respuestas Frecuentes\u2014Control Migratorio TCT","year":"2025"},{"key":"ref61","volume-title":"LOPD_Ecuador: Synthetic Legal QA Dataset for Ecuadorian Data Protection Law","author":"Garca-Montero","year":"2025"},{"key":"ref62","article-title":"Banishing LLM hallucinations requires rethinking generalization","author":"Li","year":"2024","journal-title":"arXiv:2406.17642"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1020592"},{"key":"ref65","article-title":"Low-resource languages: A review of past work and future challenges","author":"Magueresse","year":"2020","journal-title":"arXiv:2006.07264"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3267618"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IALP63756.2024.10661169"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3549795"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11205497.pdf?arnumber=11205497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:52:39Z","timestamp":1761281559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11205497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3622138","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}