# Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?

arXiv: https://arxiv.org/abs/2511.21708 · HTML: https://mlsanity.com/paper/2511.21708/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 10 of 10)

- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017)
- [TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios](https://mlsanity.com/paper/2403.19318/) (2024)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [The Principles of Data-Centric AI (DCAI)](https://mlsanity.com/paper/2211.14611/) (2022)
- [AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark](https://mlsanity.com/paper/2412.06724/) (2024)
- [A Survey of Data Quality Measurement and Monitoring Tools](https://mlsanity.com/paper/1907.08138/) (2019)
- [SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines](https://mlsanity.com/paper/2401.03038/) (2024)

## Built on by (most cited first, 1 of 1)

- [Artificial Intelligence and Modeling & Simulation: An Overview](https://mlsanity.com/paper/2608.00366/) (2026)

## Abstract (arXiv)

Large language models have recently demonstrated their exceptional capabilities in supporting and automating various tasks. Among the tasks worth exploring for testing large language model capabilities, we considered data preparation, a critical yet often labor-intensive step in data-driven processes. This paper investigates whether large language models can effectively support users in selecting and automating data preparation tasks. To this aim, we considered both general-purpose and fine-tuned tabular large language models. We prompted these models with poor-quality datasets and measured their ability to perform tasks such as data profiling and cleaning. We also compare the support provided by large language models with that offered by traditional data preparation tools. To evaluate the capabilities of large language models, we developed a custom-designed quality model that has been validated through a user study to gain insights into practitioners' expectations.