@inproceedings{zhang2024benchmarking,
author = {Zhang, Yuge and Jiang, Qiyang and Han, Xingyu and Chen, Nan and Yang, Yuqing and Ren, Kan},
title = {Benchmarking Data Science Agents},
organization = {Association for Computational Linguistics},
booktitle = {The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)},
year = {2024},
month = {August},
abstract = {In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing. Yet their practical efficacy remains constrained by the varied demands of real-world applications and complicated analytical process. In this paper, we introduce DSEval -- a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the performance of these agents throughout the entire data science lifecycle. Incorporating a novel bootstrapped annotation method, we streamline dataset preparation, improve the evaluation coverage, and expand benchmarking comprehensiveness. Our findings uncover prevalent obstacles and provide critical insights to inform future advancements in the field.},
url = {http://approjects.co.za/?big=en-us/research/publication/benchmarking-data-science-agents/},
}