# Data Cleaning Using Large Language Models

arXiv: https://arxiv.org/abs/2410.15547 · HTML: https://mlsanity.com/paper/2410.15547/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2024.

## Built on by (most cited first, 7 of 7)

- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Why can't Epidemiology be automated (yet)?](https://mlsanity.com/paper/2507.15617/) (2025)
- [Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data](https://mlsanity.com/paper/2509.21465/) (2025)
- [Toward Agentic Environments: GenAI and the Convergence of AI, Sustainability, and Human-Centric Spaces](https://mlsanity.com/paper/2512.15787/) (2025)
- [BatchGen: An Architecture for Scalable and Efficient Batch Inference](https://mlsanity.com/paper/2606.21712/) (2026)
- [Artificial Intelligence and Modeling & Simulation: An Overview](https://mlsanity.com/paper/2608.00366/) (2026)
- [Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs](https://mlsanity.com/paper/2608.14765/) (2026)

## Abstract (arXiv)

Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have relied on statistical rules derived from erroneous data, resulting in low accuracy and recall. This work introduces Cocoon, a novel data cleaning system that leverages large language models for rules based on semantic understanding and combines them with statistical error detection. However, data cleaning is still too complex a task for current LLMs to handle in one shot. To address this, we introduce Cocoon, which decomposes complex cleaning tasks into manageable components in a workflow that mimics human cleaning processes. Our experiments show that Cocoon outperforms state-of-the-art data cleaning systems on standard benchmarks.