2024 · Findings of EMNLP
BLADE: Benchmarking Language Model Agents for Data-Driven Science
Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu, Yue Mao, Youran Pan, Teng Wu, Jiaqian Yu, Yikun Zhang, Tianmai M. Zhang, Lanyi Zhu, Mike A. Merrill, Jeffrey Heer, Tim Althoff
BibTeX
@inproceedings{gu2024blade,
title = {BLADE: Benchmarking Language Model Agents for Data-Driven Science},
author = {Ken Gu and Ruoxi Shang and Ruien Jiang and Keying Kuang and Richard-John Lin and Donghe Lyu and Yue Mao and Youran Pan and Teng Wu and Jiaqian Yu and Yikun Zhang and Tianmai M. Zhang and Lanyi Zhu and Mike A. Merrill and Jeffrey Heer and Tim Althoff},
year = {2024},
booktitle = {Findings of EMNLP},
doi = {10.18653/v1/2024.findings-emnlp.815},
eprint = {2408.09667},
archivePrefix = {arXiv}
}