mlsanityData to 7 Oct 2026

Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way

arXiv 2408.16119 ↗First posted 28 Aug 2024cs.HC cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Data analysts often need to iterate between data transformations and chart designs to create rich visualizations for exploratory data analysis. Although many AI-powered systems have been introduced to reduce the effort of visualization authoring, existing systems are not well suited for iterative authoring. They typically require analysts to provide, in a single turn, a text-only prompt that fully describe a complex visualization. We introduce Data Formulator 2 (DF2 for short), an AI-powered visualization system designed to overcome this limitation. DF2 blends graphical user interfaces and natural language inputs to enable users to convey their intent more effectively, while delegating data transformation to AI. Furthermore, to support efficient iteration, DF2 lets users navigate their iteration history and reuse previous designs, eliminating the need to start from scratch each time. A user study with eight participants demonstrated that DF2 allowed participants to develop their own iteration styles to complete challenging data exploration sessions.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 29 of its 73 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

29 of 73 references.

References · 29

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  5. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  8. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  10. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 242
  11. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  12. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
17 more
  1. 2023The Metacognitive Demands and Opportunities of Generative AIcited by 85
  2. 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 82
  3. 2020NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queriescited by 73
  4. 2023ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Languagecited by 71
  5. 2018Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networkscited by 47
  6. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 34
  7. 2023DirectGPT: A Direct Manipulation Interface to Interact with Large Language Modelscited by 32
  8. 2023On the Design of AI-powered Code Assistants for Notebookscited by 28
  9. 2023How Do Analysts Understand and Verify AI-Assisted Data Analyses?cited by 25
  10. 2019Multi-modal Synthesis of Regular Expressionscited by 13
  11. 2020mage: Fluid Moves Between Code and Graphical Work in Computational Notebookscited by 13
  12. 2022Facilitating Conversational Interaction in Natural Language Interfaces for Visualizationcited by 12
  13. 2021Lux: Always-on Visualization Recommendations for Exploratory Dataframe Workflowscited by 10
  14. 2021Falx: Synthesis-Powered Visualization Authoringcited by 8
  15. 2022Type-Directed Synthesis of Visualizations from Natural Language Queriescited by 5
  16. 2019Task-Oriented Optimal Sequencing of Visualization Chartscited by 4
  17. 2022Visualizing the Scripts of Data Wrangling with SOMNUScited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 13.

19 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Model-based Agents for Statistics and Data Sciencecited by 22
  2. 2025AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Sciencecited by 4
  3. 2026LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysiscited by 4
  4. 2025Challenges & Opportunities with LLM-Assisted Visualization Retargetingcited by 1
  5. 2025ORCA: ORchestrating Causal Agentcited by 1
  6. 2025A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizationscited by 1
  7. 2025YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discoverycited by 1
  8. 2026NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMscited by 1
  9. 2026VegaChat: A Robust Framework for LLM-Based Chart Generation and Assessmentcited by 1
  10. 2026DA-Studio: An Agentic System for End-to-End Data Analysiscited by 1
  11. 2026AnnoBench: A Benchmark for Visualization Annotation Generationcited by 1
  12. 2026Toward a Machine Bertin: Why Visualization Needs Design Principles for Machine Cognitioncited by 0
7 more
  1. 2026CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimizationcited by 0
  2. 2026Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specificationscited by 0
  3. 2026Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacycited by 0
  4. 2026MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systemscited by 0
  5. 2026AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysiscited by 0
  6. 2026Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptationcited by 0
  7. 2026Where LLMs Fail with Visualization DSLscited by 0