Position Paper: Data-Centric AI in the Age of Large Language Models

2024 inproceedings xu2024dcaillm ○ Not yet verified

Authors

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, Bryan Kian Hsiang Low

Venue

EMNLP Findings

Abstract

Position paper identifying four specific scenarios centered around data for LLMs, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization.

BibTeX

Local Entry

@inproceedings{xu2024dcaillm,
  title = {Position Paper: Data-Centric AI in the Age of Large Language Models},
  author = {Xinyi Xu and Zhaoxuan Wu and Rui Qiao and Arun Verma and Yao Shu and Jingtan Wang and Xinyuan Niu and Zhenfeng He and Jiangwei Chen and Zijian Zhou and Gregory Kang Ruey Lau and Hieu Dao and Lucas Agussurja and Rachael Hwee Ling Sim and Xiaoqiang Lin and Wenyang Hu and Zhongxiang Dai and Pang Wei Koh and Bryan Kian Hsiang Low},
  year = {2024},
  booktitle = {EMNLP Findings},
  url = {https://aclanthology.org/2024.findings-emnlp.695/},
  abstract = {Position paper identifying four specific scenarios centered around data for LLMs, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization.}
}

From AUTO:OPENALEX

@inproceedings{xu2024dcaillm,
  title = {Position Paper: Data-Centric AI in the Age of Large Language Models},
  author = {Xinyi Xu and Zhaoxuan Wu and Rui Qiao and Arun Verma and Yao Shu and Jingtan Wang and Xinyuan Niu and Zhenfeng He and Jiangwei Chen and Zijian Zhou and Gregory Kang Ruey Lau and Hieu Dao and Lucas Agussurja and Rachael Hwee Ling Sim and Xiaoqiang Lin and Wenyang Hu and Zhongxiang Dai and Pang Wei Koh and Bryan Kian Hsiang Low},
  year = {2024},
  doi = {10.18653/v1/2024.findings-emnlp.695}
}