AAAI 2026technical0 citations

Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study

Yuqi Zhu, Yi Zhong, Jintian Zhang, Ziheng Zhang, Shuofei Qiao, Yujie Luo, Lun Du, Da Zheng

Abstract

Large Language Models (LLMs) hold promise in automating data analysis tasks, yet open-source models face significant limitations in these kinds of reasoning-intensive scenarios. In this work, we investigate strategies to enhance the data analysis capabilities of open-source LLMs. By curating a seed dataset of diverse, realistic scenarios, we evaluate models across three dimensions: data understanding, code generation, and strategic planning. Our analysis reveals three key findings: (1) Strategic planning quality serves as the primary determinant of model performance; (2) Interaction design and task complexity significantly influence reasoning capabilities; (3) Data quality demonstrates a greater impact than diversity in achieving optimal performance. We leverage these insights to develop a data synthesis methodology, demonstrating significant improvements in open-source LLMs

BibTeX
@inproceedings{aaai2026_whydoopensourcel,
  title = {Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study},
  author = {Yuqi Zhu and Yi Zhong and Jintian Zhang and Ziheng Zhang and Shuofei Qiao and Yujie Luo and Lun Du and Da Zheng and Ningyu Zhang and Huajun Chen},
  booktitle = {AAAI 2026},
  year = {2026}
}