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

arXiv: https://arxiv.org/abs/2502.02329 · HTML: https://mlsanity.com/paper/2502.02329/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 73 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 27 of 27)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models](https://mlsanity.com/paper/2303.02927/) (2023)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [Is GPT-4 a Good Data Analyst?](https://mlsanity.com/paper/2305.15038/) (2023)
- [Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models](https://mlsanity.com/paper/2305.11483/) (2023)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Calliope: Automatic Visual Data Story Generation from a Spreadsheet](https://mlsanity.com/paper/2010.09975/) (2020)
- [HAIChart: Human and AI Paired Visualization System](https://mlsanity.com/paper/2406.11033/) (2024)
- [DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts](https://mlsanity.com/paper/2408.05346/) (2024)
- [DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles](https://mlsanity.com/paper/2308.04076/) (2023)
- [Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks](https://mlsanity.com/paper/2102.12592/) (2021)
- [Retrieve-Then-Adapt: Example-based Automatic Generation for Proportion-related Infographics](https://mlsanity.com/paper/2008.01177/) (2020)
- [Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration](https://mlsanity.com/paper/2309.15723/) (2023)
- [Erato: Cooperative Data Story Editing via Fact Interpolation](https://mlsanity.com/paper/2209.02529/) (2022)
- [InkSight: Leveraging Sketch Interaction for Documenting Chart Findings in Computational Notebooks](https://mlsanity.com/paper/2307.07922/) (2023)
- [EDAssistant: Supporting Exploratory Data Analysis in Computational Notebooks with In-Situ Code Search and Recommendation](https://mlsanity.com/paper/2112.07858/) (2021)
- [Reviving Static Charts into Live Charts](https://mlsanity.com/paper/2309.02967/) (2023)
- [Conversational AI Threads for Visualizing Multidimensional Datasets](https://mlsanity.com/paper/2311.05590/) (2023)
- [Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling](https://mlsanity.com/paper/2304.08366/) (2023)
- [CrossData: Leveraging Text-Data Connections for Authoring Data Documents](https://mlsanity.com/paper/2310.11639/) (2023)
- [Code Duplication and Reuse in Jupyter Notebooks](https://mlsanity.com/paper/2005.13709/) (2020)
- [MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization](https://mlsanity.com/paper/2209.05739/) (2022)
- [Calliope-Net: Automatic Generation of Graph Data Facts via Annotated Node-link Diagrams](https://mlsanity.com/paper/2308.06441/) (2023)
- [ScrollyVis: Interactive visual authoring of guided dynamic narratives for scientific scrollytelling](https://mlsanity.com/paper/2207.03616/) (2022)
- [Code Code Evolution: Understanding How People Change Data Science Notebooks Over Time](https://mlsanity.com/paper/2209.02851/) (2022)

## Built on by (most cited first, 2 of 2)

- [Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework](https://mlsanity.com/paper/2606.29808/) (2026)
- [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026)

## Abstract (arXiv)

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.