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

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.

References in corpus (11)

• Calliope: Automatic Visual Data Story Generation from a Spreadsheet
• Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models
• ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language
• Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks
• Erato: Cooperative Data Story Editing via Fact Interpolation
• CrossData: Leveraging Text-Data Connections for Authoring Data Documents
• LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution
• HAIChart: Human and AI Paired Visualization System
• Reviving Static Charts into Live Charts
• Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling
• Conversational AI Threads for Visualizing Multidimensional Datasets

Cited by in corpus (1)

• Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework