@inproceedings{xu-etal-2024-position,
title = "Position Paper: Data-Centric {AI} in the Age of Large Language Models",
author = "Xu, Xinyi and
Wu, Zhaoxuan and
Qiao, Rui and
Verma, Arun and
Shu, Yao and
Wang, Jingtan and
Niu, Xinyuan and
He, Zhenfeng and
Chen, Jiangwei and
Zhou, Zijian and
Lau, Gregory Kang Ruey and
Dao, Hieu and
Agussurja, Lucas and
Sim, Rachael Hwee Ling and
Lin, Xiaoqiang and
Hu, Wenyang and
Dai, Zhongxiang and
Koh, Pang Wei and
Low, Bryan Kian Hsiang",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.695/",
doi = "10.18653/v1/2024.findings-emnlp.695",
pages = "11895--11913",
abstract = "This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making a key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and advocate that data-centric research should receive more attention from the community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-position">
<titleInfo>
<title>Position Paper: Data-Centric AI in the Age of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoxuan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingtan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyuan</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenfeng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangwei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijian</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregory</namePart>
<namePart type="given">Kang</namePart>
<namePart type="given">Ruey</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Agussurja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachael</namePart>
<namePart type="given">Hwee</namePart>
<namePart type="given">Ling</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqiang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongxiang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pang</namePart>
<namePart type="given">Wei</namePart>
<namePart type="family">Koh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Kian</namePart>
<namePart type="given">Hsiang</namePart>
<namePart type="family">Low</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making a key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and advocate that data-centric research should receive more attention from the community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research.</abstract>
<identifier type="citekey">xu-etal-2024-position</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.695</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.695/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11895</start>
<end>11913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Position Paper: Data-Centric AI in the Age of Large Language Models
%A Xu, Xinyi
%A Wu, Zhaoxuan
%A Qiao, Rui
%A Verma, Arun
%A Shu, Yao
%A Wang, Jingtan
%A Niu, Xinyuan
%A He, Zhenfeng
%A Chen, Jiangwei
%A Zhou, Zijian
%A Lau, Gregory Kang Ruey
%A Dao, Hieu
%A Agussurja, Lucas
%A Sim, Rachael Hwee Ling
%A Lin, Xiaoqiang
%A Hu, Wenyang
%A Dai, Zhongxiang
%A Koh, Pang Wei
%A Low, Bryan Kian Hsiang
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F xu-etal-2024-position
%X This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making a key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and advocate that data-centric research should receive more attention from the community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research.
%R 10.18653/v1/2024.findings-emnlp.695
%U https://aclanthology.org/2024.findings-emnlp.695/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.695
%P 11895-11913
Markdown (Informal)
[Position Paper: Data-Centric AI in the Age of Large Language Models](https://aclanthology.org/2024.findings-emnlp.695/) (Xu et al., Findings 2024)
ACL
- Xinyi Xu, Zhaoxuan Wu, Rui Qiao, Arun Verma, Yao Shu, Jingtan Wang, Xinyuan Niu, Zhenfeng He, Jiangwei Chen, Zijian Zhou, Gregory Kang Ruey Lau, Hieu Dao, Lucas Agussurja, Rachael Hwee Ling Sim, Xiaoqiang Lin, Wenyang Hu, Zhongxiang Dai, Pang Wei Koh, and Bryan Kian Hsiang Low. 2024. Position Paper: Data-Centric AI in the Age of Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11895–11913, Miami, Florida, USA. Association for Computational Linguistics.