ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs

TL;DR

ReSpark uses large language models to extract and adapt analysis logic from existing reports, helping users generate new data reports more efficiently and interactively, reducing manual effort.

Contribution

The paper introduces ReSpark, a novel system that leverages LLMs to reverse-engineer and adapt analysis logic from reports for new datasets, facilitating easier report creation.

Findings

ReSpark effectively generates draft analysis steps for new datasets.

User studies show ReSpark reduces time and effort in report generation.

ReSpark improves user experience with interactive refinement features.

Abstract

Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis logic-from defining objectives and transforming data to identifying and communicating insights. Manually crafting this logic can be cognitively demanding. While experienced analysts often reuse scripts from past projects, finding a perfect match for a new dataset is rare. Even when similar analyses are available online, they usually share only results or visualizations, not the underlying code, making reuse difficult. To address this, we present ReSpark, a system that leverages large language models (LLMs) to reverse-engineer analysis logic from existing reports and adapt it to new datasets. By generating draft analysis steps, ReSpark provides a warm start for users. It also supports interactive refinement, allowing users to inspect intermediate outputs, insert objectives, and revise content. We evaluate ReSpark through comparative and user studies, demonstrating its effectiveness in lowering the barrier to generating data reports without relying on existing analysis code.