@inproceedings{kim-etal-2025-lp, title = "{LP} Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models", author = "Kim, Yungi and Ha, Hyunsoo and Yang, Seonghoon and Lee, Sukyung and Kim, Jihoo and Park, Chanjun", editor = "Potdar, Saloni and Rojas-Barahona, Lina and Montella, Sebastien", booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track", month = nov, year = "2025", address = "Suzhou (China)", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.11/", pages = "158--172", ISBN = "979-8-89176-333-3" }