mlsanityData to 14 Oct 2026

Data Formulator: AI-powered Concept-driven Visualization Authoring

arXiv 2309.10094 ↗First posted 18 Sep 2023cs.HC cs.AIcited by 32

Not on the map. Why?

Abstract (arXiv)

With most modern visualization tools, authors need to transform their data into tidy formats to create visualizations they want. Because this requires experience with programming or separate data processing tools, data transformation remains a barrier in visualization authoring. To address this challenge, we present a new visualization paradigm, concept binding, that separates high-level visualization intents and low-level data transformation steps, leveraging an AI agent. We realize this paradigm in Data Formulator, an interactive visualization authoring tool. With Data Formulator, authors first define data concepts they plan to visualize using natural languages or examples, and then bind them to visual channels. Data Formulator then dispatches its AI-agent to automatically transform the input data to surface these concepts and generate desired visualizations. When presenting the results (transformed table and output visualizations) from the AI agent, Data Formulator provides feedback to help authors inspect and understand them. A user study with 10 participants shows that participants could learn and use Data Formulator to create visualizations that involve challenging data transformations, and presents interesting future research directions.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 26 of its 70 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

26 of 70 references.

References · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  4. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  5. 2021Measuring Coding Challenge Competence With APPScited by 902
  6. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  7. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  8. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  9. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 218
  10. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  11. 2023LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Modelscited by 82
  12. 2020NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queriescited by 74
14 more
  1. 2018Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networkscited by 48
  2. 2021Collecting and Characterizing Natural Language Utterances for Specifying Data Visualizationscited by 31
  3. 2019Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrationscited by 26
  4. 2020mage: Fluid Moves Between Code and Graphical Work in Computational Notebookscited by 13
  5. 2021Lux: Always-on Visualization Recommendations for Exploratory Dataframe Workflowscited by 10
  6. 2021Falx: Synthesis-Powered Visualization Authoringcited by 8
  7. 2022Type-Directed Synthesis of Visualizations from Natural Language Queriescited by 5
  8. 2019Critical Reflections on Visualization Authoring Systemscited by 4
  9. 2019Visualization by Examplecited by 3
  10. 2020Lyra 2: Designing Interactive Visualizations by Demonstrationcited by 3
  11. 2022Animated Vega-Lite: Unifying Animation with a Grammar of Interactive Graphicscited by 3
  12. 2021Untidy Data: The Unreasonable Effectiveness of Tablescited by 2
  13. 2021Deconstructing Categorization in Visualization Recommendation: A Taxonomy and Comparative Studycited by 1
  14. 2022Revealing the Semantics of Data Wrangling Scripts With COMANTICScited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 11; 2026: 15.

32 papers.

Sort:

By area:

  1. 2025nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflowcited by 23
  2. 2024Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualizationcited by 14
  3. 2025Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systemscited by 12
  4. 2024GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstructioncited by 7
  5. 2024Data Analysis in the Era of Generative AIcited by 6
  6. 2025Exploring Multimodal Prompt for Visualization Authoring with Large Language Modelscited by 5
  7. 2025Multi-Agent Data Visualization and Narrative Generationcited by 4
  8. 2024Contextualized Data-Wrangling Code Generation in Computational Notebookscited by 3
  9. 2024HINTs: Sensemaking on large collections of documents with Hypergraph visualization and INTelligent agentscited by 2
  10. 2025ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMscited by 2
  11. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  12. 2025MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Modelcited by 1
20 more
  1. 2025Challenges & Opportunities with LLM-Assisted Visualization Retargetingcited by 1
  2. 2025A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizationscited by 1
  3. 2025YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discoverycited by 1
  4. 2024Evaluating the Semantic Profiling Abilities of LLMs for Natural Language Utterances in Data Visualizationcited by 0
  5. 2025Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Modelscited by 0
  6. 2026From Static to Interactive: Authoring Interactive Visualizations via Natural Languagecited by 0
  7. 2026Toward Reliable Scientific Visualization Pipeline Construction with Structure-Aware Retrieval-Augmented LLMscited by 0
  8. 2026Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systemscited by 0
  9. 2026Show Me the Infographic I Imagine: Intent-Aware Infographic Retrieval for Authoring Supportcited by 0
  10. 2026Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacycited by 0
  11. 2026MV-Bench: Benchmarking Multimodal Large Language Models for Coordinated Multi-View Interface Constructioncited by 0
  12. 2026MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systemscited by 0
  13. 2026AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysiscited by 0
  14. 2026Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualizationcited by 0
  15. 2026DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?cited by 0
  16. 2026Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysiscited by 0
  17. 2026AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysiscited by 0
  18. 2026VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queriescited by 0
  19. 2026Where LLMs Fail with Visualization DSLscited by 0
  20. 2026A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBraincited by 0