Towards Natural Language Interfaces for Data Visualization: A Survey
Not on the map. Why?
Abstract (arXiv)
Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience. It enables users to focus on their tasks rather than having to worry about how to operate visualization tools on the interface. In the past two decades, leveraging advanced natural language processing technologies, numerous V-NLI systems have been developed in academic research and commercial software, especially in recent years. In this article, we conduct a comprehensive review of the existing V-NLIs. In order to classify each paper, we develop categorical dimensions based on a classic information visualization pipeline with the extension of a V-NLI layer. The following seven stages are used: query interpretation, data transformation, visual mapping, view transformation, human interaction, dialogue management, and presentation. Finally, we also shed light on several promising directions for future work in the V-NLI community.
Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Sep 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 5; 2023: 7; 2024: 15; 2025: 21; 2026: 11.
59 papers.
Sort:
By area:
- 2023Data-centric Artificial Intelligence: A Surveycited by 203
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 53
- 2024ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answeringcited by 50
- 2024VisEval: A Benchmark for Data Visualization in the Era of Large Language Modelscited by 45
- 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualizationcited by 39
- 2023Foundation Models Meet Visualizations: Challenges and Opportunitiescited by 31
- 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
- 2024Are Large Language Models Good Statisticians?cited by 27
- 2022Chart Question Answering: State of the Art and Future Directionscited by 26
- 2023DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articlescited by 24
38 more
- 2024Generative AI for Visualization: State of the Art and Future Directionscited by 23
- 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splattingcited by 20
- 2023XNLI: Explaining and Diagnosing NLI-based Visual Data Analysiscited by 19
- 2024From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systemscited by 16
- 2025CoDA: Agentic Systems for Collaborative Data Visualizationcited by 15
- 2025InterChat: Enhancing Generative Visual Analytics using Multimodal Interactionscited by 13
- 2022Pair-Level Supervised Contrastive Learning for Natural Language Inferencecited by 12
- 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
- 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
- 2022A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inferencecited by 8
- 2023Conversational AI Threads for Visualizing Multidimensional Datasetscited by 8
- 2025VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualizationcited by 8
- 2025DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoningcited by 8
- 2024Data Analysis in the Era of Generative AIcited by 6
- 2024Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directionscited by 6
- 2025Explainable XR: Understanding User Behaviors of XR Environments using LLM-assisted Analytics Frameworkcited by 6
- 2025ChartMark: A Structured Grammar for Chart Annotationcited by 6
- 2022Using Large Language Models to Generate Engaging Captions for Data Visualizationscited by 5
- 2024Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLMcited by 5
- 2025ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understandingcited by 5
- 2025Evaluating LLMs for Visualization Generation and Understandingcited by 5
- 2026Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemakingcited by 4
- 2024Generating Tables from the Parametric Knowledge of Language Modelscited by 3
- 2023InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMscited by 2
- 2024LLM-Assisted Visual Analytics: Opportunities and Challengescited by 2
- 2024Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizationscited by 2
- 2026Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualizationcited by 2
- 2025MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Modelcited by 1
- 2025A Review on Large Language Models for Visual Analyticscited by 1
- 2025Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insightscited by 1
- 2025ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasetscited by 1
- 2025Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analyticscited by 1
- 2025A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizationscited by 1
- 2025YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discoverycited by 1
- 2026NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMscited by 1
- 2026LangLasso: Interactive Cluster Descriptions through LLM Explanationcited by 1
- 2026The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Qualitycited by 1
- 2024Macro-Queries: An Exploration into Guided Chart Generation from High Level Promptscited by 0
50 most cited of 59 All 59 (JSON)
- 2026DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis2 Oct 2026
- 2026Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets22 Aug 2026
- 2026Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualization21 Aug 2026
- 2026MV-Bench: Benchmarking Multimodal Large Language Models for Coordinated Multi-View Interface Construction22 Jul 2026
- 2026Comparing LLM-Based Conversational and Graphical Interfaces for Industrial Decision Tasks: An Exploratory Mixed-Methods Study29 May 2026
- 2026The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality26 Jan 2026
- 2026From Static to Interactive: Authoring Interactive Visualizations via Natural Language25 Jan 2026
- 2026Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemaking16 Jan 2026
- 2026LangLasso: Interactive Cluster Descriptions through LLM Explanation15 Jan 2026
- 2026Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization8 Jan 2026
- 2026NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs4 Jan 2026
- 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?27 Oct 2025
38 more
- 2025CoDA: Agentic Systems for Collaborative Data Visualization3 Oct 2025
- 2025YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery23 Sep 2025
- 2025A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizations19 Sep 2025
- 2025Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics10 Aug 2025
- 2025ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasets8 Aug 2025
- 2025DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning3 Aug 2025
- 2025ChartMark: A Structured Grammar for Chart Annotation29 Jul 2025
- 2025Automated Visualization Makeovers with LLMs21 Jul 2025
- 2025VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization18 Jul 2025
- 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting16 Jul 2025
- 2025Evaluating LLMs for Visualization Generation and Understanding16 Jun 2025
- 2025ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding21 May 2025
- 2025Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights15 May 2025
- 2025DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent24 Apr 2025
- 2025Evaluating LLMs for Visualization Tasks10 Apr 2025
- 2025A Survey of Scaling in Large Language Model Reasoning2 Apr 2025
- 2025A Review on Large Language Models for Visual Analytics19 Mar 2025
- 2025InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions6 Mar 2025
- 2025Explainable XR: Understanding User Behaviors of XR Environments using LLM-assisted Analytics Framework23 Jan 2025
- 2025MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model2 Jan 2025
- 2024Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM18 Oct 2024
- 2024Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions29 Sep 2024
- 2024Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations27 Sep 2024
- 2024Data Analysis in the Era of Generative AI27 Sep 2024
- 2024LLM-Assisted Visual Analytics: Opportunities and Challenges4 Sep 2024
- 2024Macro-Queries: An Exploration into Guided Chart Generation from High Level Prompts22 Aug 2024
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?9 Aug 2024
- 2024From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems7 Aug 2024
- 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization3 Aug 2024
- 2024VisEval: A Benchmark for Data Visualization in the Era of Large Language Models1 Jul 2024
- 2024Generating Tables from the Parametric Knowledge of Language Models16 Jun 2024
- 2024Are Large Language Models Good Statisticians?12 Jun 2024
- 2024ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering11 May 2024
- 2024Generative AI for Visualization: State of the Art and Future Directions28 Apr 2024
- 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models18 Mar 2024
- 2023InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs15 Dec 2023
- 2023Conversational AI Threads for Visualizing Multidimensional Datasets9 Nov 2023
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey27 Oct 2023
50 newest of 59 All 59 (JSON)
- 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualizationcited by 39
- 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
- 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splattingcited by 20
- 2024From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systemscited by 16
- 2025CoDA: Agentic Systems for Collaborative Data Visualizationcited by 15
- 2025VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualizationcited by 8
- 2026The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Qualitycited by 1
- 2025DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agentcited by 0
- 2026Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualizationcited by 0
- 2026Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualization21 Aug 2026
- 2026The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality26 Jan 2026
- 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?27 Oct 2025
- 2025CoDA: Agentic Systems for Collaborative Data Visualization3 Oct 2025
- 2025VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization18 Jul 2025
- 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting16 Jul 2025
- 2025DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent24 Apr 2025
- 2024From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems7 Aug 2024
- 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization3 Aug 2024
- 2023Data-centric Artificial Intelligence: A Surveycited by 203
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 53
- 2024VisEval: A Benchmark for Data Visualization in the Era of Large Language Modelscited by 45
- 2023Foundation Models Meet Visualizations: Challenges and Opportunitiescited by 31
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
- 2024Are Large Language Models Good Statisticians?cited by 27
- 2022Chart Question Answering: State of the Art and Future Directionscited by 26
- 2023DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articlescited by 24
- 2024Generative AI for Visualization: State of the Art and Future Directionscited by 23
- 2023XNLI: Explaining and Diagnosing NLI-based Visual Data Analysiscited by 19
- 2025InterChat: Enhancing Generative Visual Analytics using Multimodal Interactionscited by 13
12 most cited of 45 All 45 (JSON)
- 2026DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis2 Oct 2026
- 2026Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets22 Aug 2026
- 2026Comparing LLM-Based Conversational and Graphical Interfaces for Industrial Decision Tasks: An Exploratory Mixed-Methods Study29 May 2026
- 2026From Static to Interactive: Authoring Interactive Visualizations via Natural Language25 Jan 2026
- 2026Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemaking16 Jan 2026
- 2026LangLasso: Interactive Cluster Descriptions through LLM Explanation15 Jan 2026
- 2026Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization8 Jan 2026
- 2026NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs4 Jan 2026
- 2025YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery23 Sep 2025
- 2025A Generative AI System for Biomedical Data Discovery with Grammar-Based Visualizations19 Sep 2025
- 2025Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics10 Aug 2025
- 2025ClimateSOM: A Visual Analysis Workflow for Climate Ensemble Datasets8 Aug 2025
12 newest of 45 All 45 (JSON)