# LLMClean: Context-Aware Tabular Data Cleaning via LLM-Generated OFDs

arXiv: https://arxiv.org/abs/2404.18681 · HTML: https://mlsanity.com/paper/2404.18681/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2024.

## Built on by (most cited first, 19 of 19)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark](https://mlsanity.com/paper/2412.06724/) (2024)
- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [JITServe: SLO-aware LLM Serving with Imprecise Request Information](https://mlsanity.com/paper/2504.20068/) (2025)
- [On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing](https://mlsanity.com/paper/2501.02191/) (2025)
- [Graph-based Confidence Calibration for Large Language Models](https://mlsanity.com/paper/2411.02454/) (2024)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [Autonomous Data Agents: A New Opportunity for Smart Data](https://mlsanity.com/paper/2509.18710/) (2025)
- [Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models](https://mlsanity.com/paper/2409.20135/) (2024)
- [Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE](https://mlsanity.com/paper/2505.23868/) (2025)
- [AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge](https://mlsanity.com/paper/2406.19271/) (2024)
- [Towards Practical Benchmarking of Data Cleaning Techniques: On Generating Authentic Errors via Large Language Models](https://mlsanity.com/paper/2507.10934/) (2025)
- [Why can't Epidemiology be automated (yet)?](https://mlsanity.com/paper/2507.15617/) (2025)
- [CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes](https://mlsanity.com/paper/2606.31435/) (2026)
- [ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows](https://mlsanity.com/paper/2605.12376/) (2026)
- [TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification](https://mlsanity.com/paper/2608.11044/) (2026)
- [Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs](https://mlsanity.com/paper/2608.14765/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

Machine learning's influence is expanding rapidly, now integral to decision-making processes from corporate strategy to the advancements in Industry 4.0. The efficacy of Artificial Intelligence broadly hinges on the caliber of data used during its training phase; optimal performance is tied to exceptional data quality. Data cleaning tools, particularly those that exploit functional dependencies within ontological frameworks or context models, are instrumental in augmenting data quality. Nevertheless, crafting these context models is a demanding task, both in terms of resources and expertise, often necessitating specialized knowledge from domain experts. In light of these challenges, this paper introduces an innovative approach, called LLMClean, for the automated generation of context models, utilizing Large Language Models to analyze and understand various datasets. LLMClean encompasses a sequence of actions, starting with categorizing the dataset, extracting or mapping relevant models, and ultimately synthesizing the context model. To demonstrate its potential, we have developed and tested a prototype that applies our approach to three distinct datasets from the Internet of Things, healthcare, and Industry 4.0 sectors. The results of our evaluation indicate that our automated approach can achieve data cleaning efficacy comparable with that of context models crafted by human experts.