Flowco: Rethinking Data Analysis in the Age of LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Freund, Stephen N., Simon, Brooke, Berger, Emery D., Jun, Eunice
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909584655908864
author Freund, Stephen N.
Simon, Brooke
Berger, Emery D.
Jun, Eunice
author_facet Freund, Stephen N.
Simon, Brooke
Berger, Emery D.
Jun, Eunice
contents Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize data science by enabling those with limited programming expertise to conduct data analyses, including in scientific research, business, and policymaking. However, analysts in many real-world settings must often exercise fine-grained control over specific analysis steps, verify intermediate results explicitly, and iteratively refine their analytical approaches. Such tasks present barriers to building robust and reproducible analyses using LLMs alone or even in conjunction with existing authoring tools (e.g., computational notebooks). This paper introduces Flowco, a new mixed-initiative system to address these challenges. Flowco leverages a visual dataflow programming model and integrates LLMs into every phase of the authoring process. A user study suggests that Flowco supports analysts, particularly those with less programming experience, in quickly authoring, debugging, and refining data analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14038
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flowco: Rethinking Data Analysis in the Age of LLMs
Freund, Stephen N.
Simon, Brooke
Berger, Emery D.
Jun, Eunice
Human-Computer Interaction
Artificial Intelligence
Programming Languages
Computation
Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such code for simple, routine analyses. LLMs promise to democratize data science by enabling those with limited programming expertise to conduct data analyses, including in scientific research, business, and policymaking. However, analysts in many real-world settings must often exercise fine-grained control over specific analysis steps, verify intermediate results explicitly, and iteratively refine their analytical approaches. Such tasks present barriers to building robust and reproducible analyses using LLMs alone or even in conjunction with existing authoring tools (e.g., computational notebooks). This paper introduces Flowco, a new mixed-initiative system to address these challenges. Flowco leverages a visual dataflow programming model and integrates LLMs into every phase of the authoring process. A user study suggests that Flowco supports analysts, particularly those with less programming experience, in quickly authoring, debugging, and refining data analyses.
title Flowco: Rethinking Data Analysis in the Age of LLMs
topic Human-Computer Interaction
Artificial Intelligence
Programming Languages
Computation
url https://arxiv.org/abs/2504.14038