{"id":931371,"date":"2023-03-28T13:43:57","date_gmt":"2023-03-28T20:43:57","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=931371"},"modified":"2024-01-25T08:23:15","modified_gmt":"2024-01-25T16:23:15","slug":"lida-automatic-generation-of-grammar-agnostic-visualizations","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/lida-automatic-generation-of-grammar-agnostic-visualizations\/","title":{"rendered":"LIDA: Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background-grey card-background--full-bleed\">\n\t\t\t\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 \">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h2 class=\"wp-block-heading\" id=\"lida\">LIDA<\/h2>\n\n\n\n<p>Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>Systems that support users in the automatic creation of visualizations must address several subtasks &#8211; understand the semantics of data, enumerate relevant visualization goals and generate visualization specifications. In this work, we\u00a0pose visualization generation as a multi-stage generation problem\u00a0and argue that well-orchestrated pipelines based on large language models (LLMs) and image generation models (IGMs) are suitable to addressing these tasks. We present LIDA, a novel tool for generating grammar-agnostic visualizations and infographics. LIDA comprises of 4 modules &#8211; A SUMMARIZER that converts data into a rich but compact natural language summary, a GOAL EXPLORER that enumerates visualization goals given the data, a VISGENERATOR that generates, refines, executes and filters visualization code and an INFOGRAPHER module that yields data-faithful stylized graphics using IGMs. LIDA provides a python api, and a hybrid user interface (direct manipulation and\u00a0multilingual\u00a0natural language) for interactive chart, infographics and data story generation.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/microsoft.github.io\/lida\/\" target=\"_blank\" rel=\"noreferrer noopener\">Learn more<\/a><\/div>\n<\/div>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models Systems that support users in the automatic creation of visualizations must address several subtasks &#8211; understand the semantics of data, enumerate relevant visualization goals and generate visualization specifications. In this work, we\u00a0pose visualization generation as a multi-stage generation problem\u00a0and argue that well-orchestrated pipelines based [&hellip;]<\/p>\n","protected":false},"featured_media":931380,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-931371","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2022-10-01","related-publications":[932820],"related-downloads":[966237],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Victor Dibia","user_id":41311,"people_section":"Related people","alias":"victordibia"}],"msr_research_lab":[199565,992148],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/931371"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":8,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/931371\/revisions"}],"predecessor-version":[{"id":1001904,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/931371\/revisions\/1001904"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/931380"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=931371"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=931371"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=931371"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=931371"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=931371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}