{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:54:54Z","timestamp":1772934894570,"version":"3.50.1"},"reference-count":23,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402145","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5490-5499","source":"Crossref","is-referenced-by-count":0,"title":["Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysis"],"prefix":"10.1109","author":[{"given":"Felipe Ribeiro Fujita","family":"de Mello","sequence":"first","affiliation":[{"name":"Ritsumeikan University,Osaka,Japan"}]},{"given":"Hideyuki","family":"Takada","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Osaka,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.24"},{"key":"ref2","first-page":"355","article-title":"Domain Adaptation via Pseudo In-Domain Data Selection","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"Axelrod","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1319"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.wmt-1.52"},{"key":"ref5","article-title":"Intelligent Selection of Language Model Training Data","volume-title":"Proceedings of the ACL 2010 Conference Short Papers, pages 220\u2013224","author":"Moore","year":"2010"},{"key":"ref6","article-title":"A Comparative Study on TF-IDF Feature Weighting Method and Its Analysis Using Unstructured Dataset","volume-title":"International Conference on Computational Linguistics and Intelligent Systems","author":"Das","year":"2023"},{"key":"ref7","first-page":"726","article-title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Nguyen","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wmt-1.52"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wmt-1.60"},{"key":"ref10","first-page":"34201","article-title":"Data selection for language models via importance resampling","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923)","author":"Xie","year":"2023"},{"key":"ref11","article-title":"QuRating: Selecting High-Quality Data for Training Language Models","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Wettig","year":"2024"},{"key":"ref12","first-page":"44424456","article-title":"Large Language Models are Good Multilingual Learners: When LLMs Meet Cross-Lingual Prompts","author":"Wang","year":"2025","journal-title":"Proc. of COLING"},{"key":"ref13","article-title":"Predictive Data Selection: The Data That Predicts Is the Data That Teaches","volume-title":"Proc. of ACL","author":"Shum","year":"2025"},{"key":"ref14","article-title":"A Study of Translation Edit Rate with Targeted Human Annotation","volume-title":"Proc. of AMTA","author":"Snover","year":"2006"},{"key":"ref15","article-title":"A Survey on Data Selection for Language Models","volume-title":"arXiv preprint","author":"Albalak","year":"2024"},{"key":"ref16","article-title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","volume":"abs\/1812.05159","author":"Toneva","year":"2018","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.634"},{"key":"ref18","volume-title":"The Kyoto Free Translation Task","author":"Neubig","year":"2011"},{"key":"ref19","article-title":"LLaMA: Open and Efficient Foundation Language Models","volume-title":"arXiv preprint","author":"Touvron","year":"2023"},{"key":"ref20","article-title":"Gemma: Open Models Based on Gemini Research and Technology","volume-title":"arXiv preprint","author":"Team","year":"2024"},{"key":"ref21","article-title":"Mistral 7B","volume-title":"arXiv preprint","author":"Jiang","year":"2023"},{"key":"ref22","article-title":"Qwen3 Technical Report","volume-title":"arXiv preprint","author":"Yang","year":"2025"},{"key":"ref23","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proc. of ICLR","author":"Hu","year":"2022"}],"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\/11402145.pdf?arnumber=11402145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:19:42Z","timestamp":1772867982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402145","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}