@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://aclanthology.org/2025.emnlp-industry.11/",
pages = "158--172",
ISBN = "979-8-89176-333-3",
abstract = "Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits accessibility for organizations lacking significant computational infrastructure. To address this issue, we introduce the Lightweight, Purpose-driven (LP) Data Pipeline, a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. Based on our four core principles, the LP Data Pipeline significantly reduces preparation time and cost while maintaining high data quality. Importantly, our pipeline enables the creation of purpose-driven datasets tailored to specific domains and languages, enhancing the applicability of LLMs in specialized contexts. We anticipate that our pipeline will lower the barriers to LLM development, enabling a wide range of organizations to access LLMs more easily."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-lp">
<titleInfo>
<title>LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yungi</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunsoo</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonghoon</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sukyung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits accessibility for organizations lacking significant computational infrastructure. To address this issue, we introduce the Lightweight, Purpose-driven (LP) Data Pipeline, a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. Based on our four core principles, the LP Data Pipeline significantly reduces preparation time and cost while maintaining high data quality. Importantly, our pipeline enables the creation of purpose-driven datasets tailored to specific domains and languages, enhancing the applicability of LLMs in specialized contexts. We anticipate that our pipeline will lower the barriers to LLM development, enabling a wide range of organizations to access LLMs more easily.</abstract>
<identifier type="citekey">kim-etal-2025-lp</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.11/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>158</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models
%A Kim, Yungi
%A Ha, Hyunsoo
%A Yang, Seonghoon
%A Lee, Sukyung
%A Kim, Jihoo
%A Park, Chanjun
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F kim-etal-2025-lp
%X Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits accessibility for organizations lacking significant computational infrastructure. To address this issue, we introduce the Lightweight, Purpose-driven (LP) Data Pipeline, a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. Based on our four core principles, the LP Data Pipeline significantly reduces preparation time and cost while maintaining high data quality. Importantly, our pipeline enables the creation of purpose-driven datasets tailored to specific domains and languages, enhancing the applicability of LLMs in specialized contexts. We anticipate that our pipeline will lower the barriers to LLM development, enabling a wide range of organizations to access LLMs more easily.
%U https://aclanthology.org/2025.emnlp-industry.11/
%P 158-172
Markdown (Informal)
[LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models](https://aclanthology.org/2025.emnlp-industry.11/) (Kim et al., EMNLP 2025)
ACL