# Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

arXiv: https://arxiv.org/abs/2601.17058 · HTML: https://mlsanity.com/paper/2601.17058/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 84 of its 162 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Builds on (most cited first, 30 of 84)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning](https://mlsanity.com/paper/2309.00363/) (2023)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [Synthetic Data Generation Using Large Language Models: Advances in Text and Code](https://mlsanity.com/paper/2503.14023/) (2025)
- [DeepER -- Deep Entity Resolution](https://mlsanity.com/paper/1710.00597/) (2017)
- [Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table](https://mlsanity.com/paper/2305.07288/) (2023)
- [Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost](https://mlsanity.com/paper/2306.15766/) (2023)
- [Large Language Models as Data Preprocessors](https://mlsanity.com/paper/2308.16361/) (2023)
- [Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning](https://mlsanity.com/paper/2307.02179/) (2023)
- [Entity Matching using Large Language Models](https://mlsanity.com/paper/2310.11244/) (2023)
- [Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching](https://mlsanity.com/paper/2405.16884/) (2024)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [A Comprehensive Survey of Synthetic Tabular Data Generation](https://mlsanity.com/paper/2504.16506/) (2025)
- [Agent-OM: Leveraging LLM Agents for Ontology Matching](https://mlsanity.com/paper/2312.00326/) (2023)
- [LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation](https://mlsanity.com/paper/2410.21520/) (2024)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)
- [AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark](https://mlsanity.com/paper/2412.06724/) (2024)
- [Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System](https://mlsanity.com/paper/2504.09207/) (2025)

## Built on by (most cited first, 9 of 9)

- [AgenticDataBench: A Comprehensive Benchmark for Data Agents](https://mlsanity.com/paper/2607.01647/) (2026)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis](https://mlsanity.com/paper/2605.30434/) (2026)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [Automating Database-Native Function Code Synthesis with LLMs](https://mlsanity.com/paper/2604.06231/) (2026)
- [Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System](https://mlsanity.com/paper/2603.07449/) (2026)
- [SemJoin: Semantic Join Optimization](https://mlsanity.com/paper/2606.29532/) (2026)
- [Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models](https://mlsanity.com/paper/2607.19847/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them, which is essential for a wide range of data-centric applications. Driven by (i) rising demands for application-ready data (e.g., for analytics, visualization, decision-making), (ii) increasingly powerful LLM techniques, and (iii) the emergence of infrastructures that facilitate flexible agent construction (e.g., using Databricks Unity Catalog), LLM-enhanced methods are rapidly becoming a transformative and potentially dominant paradigm for data preparation. By investigating hundreds of recent literature works, this paper presents a systematic review of this evolving landscape, focusing on the use of LLM techniques to prepare data for diverse downstream tasks. First, we characterize the fundamental paradigm shift, from rule-based, model-specific pipelines to prompt-driven, context-aware, and agentic preparation workflows. Next, we introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning (e.g., standardization, error processing, imputation), data integration (e.g., entity matching, schema matching), and data enrichment (e.g., data annotation, profiling). For each task, we survey representative techniques, and highlight their respective strengths (e.g., improved generalization, semantic understanding) and limitations (e.g., the prohibitive cost of scaling LLMs, persistent hallucinations even in advanced agents, the mismatch between advanced methods and weak evaluation). Moreover, we analyze commonly used datasets and evaluation metrics (the empirical part). Finally, we discuss open research challenges and outline a forward-looking roadmap that emphasizes scalable LLM-data systems, principled designs for reliable agentic workflows, and robust evaluation protocols.