Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Spreafico, Matteo, Tassini, Ludovica, Sancricca, Camilla, Cappiello, Cinzia
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.21708
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908677519179776
author Spreafico, Matteo
Tassini, Ludovica
Sancricca, Camilla
Cappiello, Cinzia
author_facet Spreafico, Matteo
Tassini, Ludovica
Sancricca, Camilla
Cappiello, Cinzia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?
Spreafico, Matteo
Tassini, Ludovica
Sancricca, Camilla
Cappiello, Cinzia
Computation and Language
Artificial Intelligence
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.
title Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.21708