# Large Language Models as Data Preprocessors

arXiv: https://arxiv.org/abs/2308.16361 · HTML: https://mlsanity.com/paper/2308.16361/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017)
- [Is GPT-4 a Good Data Analyst?](https://mlsanity.com/paper/2305.15038/) (2023)
- [HoloDetect: Few-Shot Learning for Error Detection](https://mlsanity.com/paper/1904.02285/) (2019)
- [DAEMA: Denoising Autoencoder with Mask Attention](https://mlsanity.com/paper/2106.16057/) (2021)

## Built on by (most cited first, 30 of 34)

- [MLZero: A Multi-Agent System for End-to-end Machine Learning Automation](https://mlsanity.com/paper/2505.13941/) (2025)
- [Jellyfish: A Large Language Model for Data Preprocessing](https://mlsanity.com/paper/2312.01678/) (2023)
- [ReMatch: Retrieval Enhanced Schema Matching with LLMs](https://mlsanity.com/paper/2403.01567/) (2024)
- [Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration](https://mlsanity.com/paper/2312.03987/) (2023)
- [A Survey on Human-Centric LLMs](https://mlsanity.com/paper/2411.14491/) (2024)
- [On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing](https://mlsanity.com/paper/2501.02191/) (2025)
- [Matchmaker: Self-Improving Large Language Model Programs for Schema Matching](https://mlsanity.com/paper/2410.24105/) (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)
- [On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach](https://mlsanity.com/paper/2401.03426/) (2024)
- [Had enough of experts? Quantitative knowledge retrieval from large language models](https://mlsanity.com/paper/2402.07770/) (2024)
- [AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science](https://mlsanity.com/paper/2502.16395/) (2025)
- [Foundation Models for Environmental Science: A Survey of Emerging Frontiers](https://mlsanity.com/paper/2504.04280/) (2025)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [Hybrid Querying Over Relational Databases and Large Language Models](https://mlsanity.com/paper/2408.00884/) (2024)
- [Large Language Models for Predictive Analysis: How Far Are They?](https://mlsanity.com/paper/2505.17149/) (2025)
- [Towards Scalable Schema Mapping using Large Language Models](https://mlsanity.com/paper/2505.24716/) (2025)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values](https://mlsanity.com/paper/2412.19113/) (2024)
- [Misinformation Detection using Large Language Models with Explainability](https://mlsanity.com/paper/2510.18918/) (2025)
- [HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery](https://mlsanity.com/paper/2601.01015/) (2026)
- [Are Large Language Models Good Data Preprocessors?](https://mlsanity.com/paper/2502.16790/) (2025)
- [A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards](https://mlsanity.com/paper/2505.13766/) (2025)
- [CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes](https://mlsanity.com/paper/2606.31435/) (2026)
- [GLARE: Guided LexRank for Advanced Retrieval in Legal Analysis](https://mlsanity.com/paper/2409.15348/) (2024)
- [1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models](https://mlsanity.com/paper/2409.20149/) (2024)
- [The Role of Accuracy and Validation Effectiveness in Conversational Business Analytics](https://mlsanity.com/paper/2411.12128/) (2024)
- [A Novel Approach to Balance Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes and its Implementation in BEACON](https://mlsanity.com/paper/2412.17910/) (2024)
- [An Interdisciplinary and Cross-Task Review on Missing Data Imputation](https://mlsanity.com/paper/2511.01196/) (2025)
- [Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance](https://mlsanity.com/paper/2511.05311/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of understanding and generating human-like text across a diverse range of topics. This study expands on the applications of LLMs, exploring their potential in data preprocessing, a critical stage in data mining and analytics applications. Aiming at tabular data, we delve into the applicability of state-of-the-art LLMs such as GPT-4 and GPT-4o for a series of preprocessing tasks, including error detection, data imputation, schema matching, and entity matching. Alongside showcasing the inherent capabilities of LLMs, we highlight their limitations, particularly in terms of computational expense and inefficiency. We propose an LLM-based framework for data preprocessing, which integrates cutting-edge prompt engineering techniques, coupled with traditional methods like contextualization and feature selection, to improve the performance and efficiency of these models. The effectiveness of LLMs in data preprocessing is evaluated through an experimental study spanning a variety of public datasets. GPT-4 emerged as a standout, achieving 100% accuracy or F1 score on 4 of these datasets, suggesting LLMs' immense potential in these tasks. Despite certain limitations, our study underscores the promise of LLMs in this domain and anticipates future developments to overcome current hurdles.