LEVA: Using Large Language Models to Enhance Visual Analytics
arXiv:2403.05816 · doi:10.1109/TVCG.2024.3368060
Abstract
Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to recall and process a significant amount of information when they visually analyze data. These challenges emphasize the need for more intelligent visual analytics methods. Large language models have demonstrated the ability to interpret various forms of textual data, offering the potential to facilitate intelligent support for visual analytics. We propose LEVA, a framework that uses large language models to enhance users' VA workflows at multiple stages: onboarding, exploration, and summarization. To support onboarding, we use large language models to interpret visualization designs and view relationships based on system specifications. For exploration, we use large language models to recommend insights based on the analysis of system status and data to facilitate mixed-initiative exploration. For summarization, we present a selective reporting strategy to retrace analysis history through a stream visualization and generate insight reports with the help of large language models. We demonstrate how LEVA can be integrated into existing visual analytics systems. Two usage scenarios and a user study suggest that LEVA effectively aids users in conducting visual analytics.
Accepted to IEEE TVCG 2024
References in corpus (14)
- NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries
- News Summarization and Evaluation in the Era of GPT-3
- Towards Natural Language Interfaces for Data Visualization: A Survey
- Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Notable: On-the-fly Assistant for Data Storytelling in Computational Notebooks
- Paths Explored, Paths Omitted, Paths Obscured: Decision Points & Selective Reporting in End-to-End Data Analysis
- Perspectives of Visualization Onboarding and Guidance in VA
- GeoCamera: Telling Stories in Geographic Visualizations with Camera Movements
- DMiner: Dashboard Design Mining and Recommendation
- Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
- TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
- Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis
- Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
Cited by in corpus (7)
- LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution
- Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models
- LLM-Assisted Visual Analytics: Opportunities and Challenges
- InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions
- VibE: A Visual Analytics Workflow for Semantic Error Analysis of CVML Models at Subgroup Level
- Challenges and Opportunities for Visual Analytics in Jurisprudence
- Supporting Multimodal Data Interaction on Refreshable Tactile Displays: An Architecture to Combine Touch and Conversational AI