# The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality

arXiv: https://arxiv.org/abs/2603.16873 · HTML: https://mlsanity.com/paper/2603.16873/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 72 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries](https://mlsanity.com/paper/2008.10723/) (2020)
- [Towards Natural Language Interfaces for Data Visualization: A Survey](https://mlsanity.com/paper/2109.03506/) (2021)
- [Chat2VIS: Generating Data Visualisations via Natural Language using ChatGPT, Codex and GPT-3 Large Language Models](https://mlsanity.com/paper/2302.02094/) (2023)
- [How do you Converse with an Analytical Chatbot? Revisiting Gricean Maxims for Designing Analytical Conversational Behavior](https://mlsanity.com/paper/2203.08420/) (2022)
- [LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution](https://mlsanity.com/paper/2411.05651/) (2024)
- [PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback](https://mlsanity.com/paper/2502.00988/) (2025)
- [Surfacing Visualization Mirages](https://mlsanity.com/paper/2001.02316/) (2020)
- [ChatVis: Automating Scientific Visualization with a Large Language Model](https://mlsanity.com/paper/2410.11863/) (2024)
- [PhenoFlow: A Human-LLM Driven Visual Analytics System for Exploring Large and Complex Stroke Datasets](https://mlsanity.com/paper/2407.16329/) (2024)
- [What May Visualization Processes Optimize?](https://mlsanity.com/paper/1506.02245/) (2015)
- [ChatVis: Large Language Model Agent for Generating Scientific Visualizations](https://mlsanity.com/paper/2507.23096/) (2025)
- [Measures in Visualization Space](https://mlsanity.com/paper/1909.05295/) (2019)
- [VizExtract: Automatic Relation Extraction from Data Visualizations](https://mlsanity.com/paper/2112.03485/) (2021)

## Built on by (most cited first, 1 of 1)

- [Beyond the Good, the Bad, and the Ugly: Colormap Assessment through Data-Aware Perceptual Metric](https://mlsanity.com/paper/2610.03720/) (2026)

## Abstract (arXiv)

Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one-shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs. Human evaluation, though effective, is costly and impractical at scale. To alleviate this problem, we propose an automated metric that evaluates visualization quality without relying on extensive human-labeled datasets. Instead, our approach uses the original underlying data as implicit ground truth. Specifically, we introduce a method that measures visualization quality by assessing the reconstruction accuracy of the original data from the visualization itself. This reconstruction-based metric provides an autonomous and scalable proxy for thorough human evaluation, facilitating more efficient and reliable AI-driven visualization workflows.