# AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark arXiv: https://arxiv.org/abs/2412.06724 ยท HTML: https://mlsanity.com/paper/2412.06724/ ## Key facts - Cited by 24 papers in the map (data through 14 Oct 2026). - Builds on 13 of its 46 references that are in the map. - First posted on arXiv 9 Dec 2024. ## Builds on (most cited first, 13 of 13) - [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024) - [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024) - [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019) - [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022) - [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024) - [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020) - [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017) - [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022) - [Low-resource Deep Entity Resolution with Transfer and Active Learning](https://mlsanity.com/paper/1906.08042/) (2019) - [Better Synthetic Data by Retrieving and Transforming Existing Datasets](https://mlsanity.com/paper/2404.14361/) (2024) - [LLMClean: Context-Aware Tabular Data Cleaning via LLM-Generated OFDs](https://mlsanity.com/paper/2404.18681/) (2024) - [Learning from Natural Language Explanations for Generalizable Entity Matching](https://mlsanity.com/paper/2406.09330/) (2024) - [KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution](https://mlsanity.com/paper/2301.04770/) (2023) ## Built on by (most cited first, 24 of 24) - [In-depth Analysis of Graph-based RAG in a Unified Framework](https://mlsanity.com/paper/2503.04338/) (2025) - [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025) - [ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.09891/) (2025) - [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025) - [Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets](https://mlsanity.com/paper/2503.06664/) (2025) - [Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework](https://mlsanity.com/paper/2604.01707/) (2026) - [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026) - [Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training](https://mlsanity.com/paper/2602.07824/) (2026) - [Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models](https://mlsanity.com/paper/2602.02039/) (2026) - [Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows](https://mlsanity.com/paper/2607.07504/) (2026) - [Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data](https://mlsanity.com/paper/2509.21465/) (2025) - [Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?](https://mlsanity.com/paper/2511.21708/) (2025) - [LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search](https://mlsanity.com/paper/2603.21530/) (2026) - [CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes](https://mlsanity.com/paper/2606.31435/) (2026) - [Autonomous Data Processing using Meta-Agents](https://mlsanity.com/paper/2602.00307/) (2026) - [ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows](https://mlsanity.com/paper/2605.12376/) (2026) - [When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning](https://mlsanity.com/paper/2606.02866/) (2026) - [An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality Assessment](https://mlsanity.com/paper/2606.13692/) (2026) - [Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization](https://mlsanity.com/paper/2606.17915/) (2026) - [AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets](https://mlsanity.com/paper/2607.15781/) (2026) - [Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks](https://mlsanity.com/paper/2607.21482/) (2026) - [CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs](https://mlsanity.com/paper/2608.00018/) (2026) - [Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs](https://mlsanity.com/paper/2608.14765/) (2026) - [Understanding Errors in LLM-Based Question Answering over Imperfect Tables](https://mlsanity.com/paper/2610.04687/) (2026) ## Abstract (arXiv) Data cleaning is a time-consuming and error-prone manual process, even with modern workflow tools such as OpenRefine. We present AutoDCWorkflow, an LLM-based pipeline for automatically generating data-cleaning workflows. The pipeline takes a raw table and a data analysis purpose, and generates a sequence of OpenRefine operations designed to produce a minimal, clean table sufficient to address the purpose. Six operations correspond to common data quality issues, including format inconsistencies, type errors, and duplicates. To evaluate AutoDCWorkflow, we create a benchmark with metrics assessing answers, data, and workflow quality for 142 purposes using 96 tables across six topics. The evaluation covers three key dimensions: (1) Purpose Answer: can the cleaned table produce a correct answer? (2) Column (Value): how closely does it match the ground truth table? (3) Workflow (Operations): to what extent does the generated workflow resemble the human-curated ground truth? Experiments show that Llama 3.1, Mistral, and Gemma 2 significantly enhance data quality, outperforming the baseline across all metrics. Gemma 2-27B consistently generates high-quality tables and answers, while Gemma 2-9B excels in producing workflows that closely resemble human-annotated versions.