{"id":860,"date":"2024-09-18T13:22:39","date_gmt":"2024-09-18T17:22:39","guid":{"rendered":"https:\/\/wordpress.cs.vt.edu\/infovis\/?page_id=860"},"modified":"2024-09-27T14:55:50","modified_gmt":"2024-09-27T18:55:50","slug":"human-ai-sensemaking","status":"publish","type":"page","link":"https:\/\/wordpress.cs.vt.edu\/infovis\/human-ai-sensemaking\/","title":{"rendered":"Visual workspaces as the common ground for Human-AI Sensemaking"},"content":{"rendered":"\n<p>Keywords: Sensemaking, Large Language Model (LLM), Visual Analytics<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Overview<\/h3>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"510\" height=\"238\" src=\"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/image-1.png\" alt=\"\" class=\"wp-image-894\" style=\"width:634px;height:auto\" srcset=\"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/image-1.png 510w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/image-1-300x140.png 300w\" sizes=\"auto, (max-width: 510px) 100vw, 510px\" \/><\/figure>\n\n\n\n<p style=\"font-size:17px\">Fig 1.An example of human visual workspace for sensemaking.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized is-style-default\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"408\" src=\"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-1024x408.png\" alt=\"\" class=\"wp-image-875\" style=\"width:500px\" srcset=\"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-1024x408.png 1024w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-300x120.png 300w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-768x306.png 768w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-1536x612.png 1536w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM-1568x625.png 1568w, https:\/\/wordpress.cs.vt.edu\/infovis\/wp-content\/uploads\/sites\/104\/2024\/09\/Screenshot-2024-09-18-at-1.29.03\u202fPM.png 2028w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p style=\"font-size:17px\">Fig 2. Our Human-AI Sensemaking framework<\/p>\n\n\n\n<div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<p>We investigate the parallels between human cognition and AI for sensemaking tasks. We focus on the commonality of the concept of Space to Think, the use of external intermediate representations, as important to both human and AI sensemaking processes.&nbsp; Empirical results demonstrate the value of Space to Think for both, and how human-generated Spaces can improve LLM performance.&nbsp; We show how Space to Think can be used as a form of common ground in visual analytics systems to enable interactive human-AI sensemaking that accelerates the overall sensemaking process.<\/p>\n\n\n\n<p><br><strong><em>papers:<\/em><\/strong><br><a href=\"https:\/\/arxiv.org\/abs\/2409.17289\" data-type=\"link\" data-id=\"https:\/\/arxiv.org\/abs\/2409.17289\">Steering LLM Summarization with Visual Workspaces for Sensemaking<\/a><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n<\/div><\/div>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Keywords: Sensemaking, Large Language Model (LLM), Visual Analytics Overview Fig 1.An example of human visual workspace for sensemaking. Fig 2. Our Human-AI Sensemaking framework We investigate the parallels between human cognition and AI for sensemaking tasks. We focus on the commonality of the concept of Space to Think, the use of external intermediate representations, as &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/wordpress.cs.vt.edu\/infovis\/human-ai-sensemaking\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Visual workspaces as the common ground for Human-AI Sensemaking&#8221;<\/span><\/a><\/p>\n","protected":false},"author":467,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-860","page","type-page","status-publish","hentry","entry"],"_links":{"self":[{"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/pages\/860","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/users\/467"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/comments?post=860"}],"version-history":[{"count":4,"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/pages\/860\/revisions"}],"predecessor-version":[{"id":1075,"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/pages\/860\/revisions\/1075"}],"wp:attachment":[{"href":"https:\/\/wordpress.cs.vt.edu\/infovis\/wp-json\/wp\/v2\/media?parent=860"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}