Pith. sign in

REVIEW 7 cited by

AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.06724 v3 pith:ACJRXITY submitted 2024-12-09 cs.DB cs.CL

AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark

classification cs.DB cs.CL
keywords dataworkflowtableautodcworkflowgemmaoperationspurposequality
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Solve the Missing First Step: Can VLMs Standardize Raw Heterogeneous Medical Data?

    cs.CV 2026-07 conditional novelty 7.0

    On MDS-Bench (1,939 raw medical standardization tasks), even Gemini 3 Flash reaches only 48.6% strict end-to-end success at producing source-grounded image-JSON pairs.

  2. Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data

    cs.LG 2025-09 unverdicted novelty 7.0

    Reasoning LLMs with minimal tools for tree construction and analysis induce decision trees that outperform CART, compete with ensembles on low-resource tabular data, and provide human-readable reasoning traces.

  3. In-depth Analysis of Graph-based RAG in a Unified Framework

    cs.IR 2025-03 unverdicted novelty 6.0

    A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.

  4. Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows

    cs.AI 2026-07 accept novelty 5.0

    Across 56 tasks, 9 model configurations, and 10,584 runs, LLM-generated skill files provided no reliable performance improvement over task-only prompting for data-science workflows.

  5. TabClean: Reusable LLM-Synthesized Programs for Tabular Data Cleaning

    cs.DB 2026-06 unverdicted novelty 5.0

    TabClean synthesizes reusable guarded Python cleaning programs from LLM reasoning on a small development set to achieve high precision and lower recurring costs on tabular data.

  6. ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

    cs.AI 2026-05 unverdicted novelty 5.0

    ProfiliTable is a multi-agent system with profiler, generator, and evaluator components that outperforms baselines on 18 tabular task types via dynamic profiling and closed-loop refinement.

  7. ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

    cs.AI 2026-05 unverdicted novelty 5.0

    ProfiliTable is a profiling-driven multi-agent system that builds semantic context through exploration and closed-loop refinement to produce more reliable tabular data transformations than prior LLM approaches.