{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:36:52Z","timestamp":1772933812395,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400860","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"2124-2129","source":"Crossref","is-referenced-by-count":0,"title":["RAILL: Retrieval-Augmented Instruction Tuning for Low-Resource Language Model Training"],"prefix":"10.1109","author":[{"given":"Youngjun","family":"Choi","sequence":"first","affiliation":[{"name":"Yonsei University,Dept. of Statistics and Data Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungjun","family":"Lim","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Statistics and Data Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhoi","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Statistics and Data Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaekyeong","family":"Jung","sequence":"additional","affiliation":[{"name":"University of Seoul,Dept. of Urban Big Data Convergence,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeKyung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,Dept. of Urban Big Data Convergence,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunsik","family":"Kim","sequence":"additional","affiliation":[{"name":"SK AX,Seongnam-si,Gyeonggi-do,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chul-su","family":"Kim","sequence":"additional","affiliation":[{"name":"BookIPs Inc.,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyongjae","family":"Lee","sequence":"additional","affiliation":[{"name":"BookIPs Inc.,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hosik","family":"Choi","sequence":"additional","affiliation":[{"name":"University of Seoul,Dept. of Urban Big Data Convergence,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungwoo","family":"Song","sequence":"additional","affiliation":[{"name":"Yonsei University,Dept. of Statistics and Data Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledgeintensive nlp tasks","volume":"33","author":"Patrick","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2024.100101"},{"key":"ref3","article-title":"AI-TA: Towards an intelligent questionanswer teaching assistant using open-source LLMs","author":"Yann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2024.100210"},{"key":"ref5","article-title":"How Do Students Interact with an LLM-powered Virtual Teaching Assistant in Different Educational Settings?","author":"Pratyusha","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Synthetic context generation for question generation","author":"Naiming","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref9","article-title":"Beyond one-model-fits-all: A survey of domain specialization for large language models","author":"Xujiang","year":"2305","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Fine-tuning large language models for domainspecific machine translation","author":"Jiawei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2024.100124"},{"key":"ref13","first-page":"39293938","article-title":"Retrieval augmented language model pre-training","volume-title":"International conference on machine learning","author":"Kelvin","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.296"},{"key":"ref15","volume-title":"Exploration and adaptation of large language models for specialized domains","author":"Betty","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Abhimanyu","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref18","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Tom","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123960"},{"key":"ref20","article-title":"A brief report on lawgpt 1.0: A virtual legal assistant based on gpt-3","author":"Ha-Thanh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"27902799","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International conference on machine learning","author":"Neil","year":"2019"},{"key":"ref22","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Xiang Lisa","year":"2021","journal-title":"arXiv preprint"},{"issue":"2","key":"ref23","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"HU","year":"2022","journal-title":"ICLR"},{"key":"ref24","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"70","author":"Hyung Won","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","article-title":"Not all languages are equal: Insights into multilingual retrieval-augmented generation","author":"Suhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Llamafactory: Unified efficient fine-tuning of 100+ language models","author":"Yaowei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","volume-title":"Hugging Face","author":"Ashvini Kumar","year":"2024"},{"key":"ref28","article-title":"Gemma2: Improving open language models at a practical size","author":"Gemma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Bertscore: Evaluating text generation with bert","author":"Tianyi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Kishore","year":"2002"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Chin-Yew","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref33","article-title":"BioASQ: A Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering","volume-title":"AAAI fall symposium: Information retrieval and knowledge discovery in biomedical text","author":"George","year":"2012"},{"key":"ref34","article-title":"Retrieval augmented generation for domainspecific question answering","author":"Sanat","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Retrieval-augmented data augmentation for lowresource domain tasks","author":"Minju","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400860.pdf?arnumber=11400860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:52:28Z","timestamp":1772866348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400860","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}