Aug 14, 2023 · LIDA is a tool to automatically explore data, generate visualizations and infographics from data using large language models like ChatGPT and GPT4

Jan 20, 2024 · In this paper, we evaluate the capability of a large language model to generate visualization specifications on the task of natural language to visualization (NL2VIS). More specifically, we have opted for GPT-3.5 and Vega-Lite to represent large language models and visualization specifications, respectively.

Aug 8, 2024 · For this study, we employ LIDA (Dibia, 2023), a novel tool designed to comprehend the semantics of data to set pertinent visualization objectives and produce visualization specifications, infographics, and data narratives. LIDA can be used with various LLM providers, including OpenAI, Azure OpenAI, PaLM, Cohere, and Huggingface, allowing for ...

Jun 25, 2024 · Recently I came across LIDA – a grammar-agnostic library designed to automatically generate data visualizations and infographics using large language models (LLMs) and Image Generation Models (IGMs). LIDA works with various large language model providers, such as OpenAI and Hugging Face.

Apr 26, 2024 · Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for …

Jan 18, 2025 · Network visualization is a cornerstone of data science and knowledge representation, offering an intuitive way to analyze relationships and patterns in complex datasets. With the rise of Large Language Models (LLMs), their integration into network analysis workflows has introduced novel capabilities, including enhanced contextual understanding ...

Mar 11, 2025 · By leveraging the capability of Large Language Model (LLM), VizAgent automates describe data, guides users’ intentions, automatically generates visualizations for specific tasks, and compares the quality of generated visualizations across different libraries.

Drawing on insights from a preliminary study, we identify self-regulated learning tasks and fine-tuning objectives to guide visualization design and tuning data construction. Our focus on aligning visualization with fine-tuned LLM makes Tailor-Mind more like a personalized tutor.

Feb 1, 2024 · Large Language Models, such as GPT-3.5, are powerful artificial intelligence models capable of understanding and generating human-like text. These models excel in natural language...

Feb 11, 2025 · We develop an iterative assistant we call "ChatVis" that can synthetically generate Python scripts for data analysis and visualization using a large language model (LLM).