Data Wrangling Task Automation Using Code-Generating Language Models

Abstract

Ensuring data quality in large tabular datasets is a critical challenge, typically addressed through data wrangling tasks. Traditional statistical methods, though efficient, cannot often understand the semantic context and deep learning approaches are resource-intensive, requiring task and dataset-specific training. We present an automated system that utilizes large language models to generate executable code for tasks like missing value imputation, error detection, and error correction. Our system aims to identify inherent patterns in the data while leveraging external knowledge, effectively addressing both memory-dependent and memory-independent tasks.

Cite

Text

Akella and Narayanam. "Data Wrangling Task Automation Using Code-Generating Language Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35344

Markdown

[Akella and Narayanam. "Data Wrangling Task Automation Using Code-Generating Language Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/akella2025aaai-data/) doi:10.1609/AAAI.V39I28.35344

BibTeX

@inproceedings{akella2025aaai-data,
  title     = {{Data Wrangling Task Automation Using Code-Generating Language Models}},
  author    = {Akella, Ashlesha and Narayanam, Krishnasuri},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {29616-29618},
  doi       = {10.1609/AAAI.V39I28.35344},
  url       = {https://mlanthology.org/aaai/2025/akella2025aaai-data/}
}