{"677762":{"#nid":"677762","#data":{"type":"event","title":"PhD Defense by Upol Ehsan ","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;Human-centered Explainable AI\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;October 31, 2024\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;9:30am-12:30pm EST\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation (Zoom only): \u003C\/strong\u003E\u003Ca href=\u0022https:\/\/us02web.zoom.us\/j\/89441246737?pwd=0Vxfp1Y0je6PKF5wElKttDXuTETPYV.1\u0022 title=\u0022https:\/\/us02web.zoom.us\/j\/89441246737?pwd=0Vxfp1Y0je6PKF5wElKttDXuTETPYV.1\u0022\u003E\u003Cstrong\u003EZoom Link\u003C\/strong\u003E\u003C\/a\u003E\u003Cstrong\u003E\u0026nbsp;|\u003C\/strong\u003E\u0026nbsp;Meeting ID: 894 4124 6737 Passcode: 325680\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EUpol Ehsan\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EPhD Candidate in Computer Science\u003C\/p\u003E\u003Cp\u003ESchool of\u0026nbsp;Interactive Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Mark O. Riedl (advisor) \u2013 School of Interactive Computing, Georgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Munmun De Choudhury\u0026nbsp;\u2013 School of Interactive Computing, Georgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Sashank Varma \u2013 School of Interactive Computing and School of Psychology, Georgia Institute of Technology\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Q. Vera Liao \u2013 Microsoft Research\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDr. Michael Muller \u2013 IBM Research\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ESummary:\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIf AI systems are going to inform consequential decisions such as deciding whether you should get a loan or receive an organ transplant, they must be explainable to \u003Cem\u003Eeveryone\u003C\/em\u003E, not just software engineers. Despite commendable technical progress in \u201copening\u201d the black-box of AI, the prevailing algorithm-centered Explainable AI (XAI) view overlooks a vital insight: \u003Cem\u003Ewho\u0026nbsp;\u003C\/em\u003Eopens the black-box matters just as much as opening it. As a result of this blind spot, many popular XAI interventions have been ineffective and even harmful in real-world settings. \u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo address the blind spot, my dissertation pioneers and operationalizes the domain of \u003Cem\u003E\u003Cstrong\u003EHuman-centered XAI\u003C\/strong\u003E\u0026nbsp;(HCXAI),\u003C\/em\u003E\u0026nbsp;a sociotechnically-informed human-centered sub-field of Explainable AI.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EThesis statement:\u0026nbsp;\u003C\/strong\u003EWith a focus on non-AI experts, this dissertation demonstrates how Human-centered XAI:\u0026nbsp;\u003C\/p\u003E\u003Col\u003E\u003Cli\u003Eexpands the design space of XAI by broadening the domain of non-algorithmic factors that augment AI explainability\u003C\/li\u003E\u003Cli\u003Eenriches our knowledge of the importance of \u201cwho\u201d the humans are in XAI design \u0026nbsp;\u003C\/li\u003E\u003Cli\u003Eenables resourceful ways to do Responsible AI by providing proactive mitigation strategies through participatory methods\u0026nbsp;\u003C\/li\u003E\u003C\/ol\u003E\u003Cp\u003EIt \u003Cstrong\u003Econtributes\u003C\/strong\u003E\u0026nbsp;1) \u003Cem\u003Econceptually:\u0026nbsp;\u003C\/em\u003Enew concepts such as such as Social Transparency that showcase \u003Cem\u003Ehow\u0026nbsp;\u003C\/em\u003Eto encode socio-organizational context to augment explainability without changing the internal model; 2) \u003Cem\u003Emethodologically:\u0026nbsp;\u003C\/em\u003Ehuman-centered evaluation of XAI, actionable frameworks, and participatory methods to co-design XAI systems; 3) \u003Cem\u003Etechnically:\u0026nbsp;\u003C\/em\u003Ecomputational techniques and design artifacts; 4) \u003Cem\u003Eempirically:\u0026nbsp;\u003C\/em\u003Efindings such as how one\u2019s AI background impacts one\u2019s interpretation of AI explanations, user perceptions of real AI users, and how AI explanations can negatively impact users despite our best intentions. \u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EImpact:\u0026nbsp;\u003C\/strong\u003EEpistemologically, the dissertation expands the XAI discourse from an algorithm-centered perspective to a human-centered one. In terms of real-world impact, the work has informed RAI policies at influential institutes like the United Nations and Mozilla Foundation. Seven Fortune100 companies have adopted the technology from my work, improving trust calibration and AI explainability of 3 million users. The work serves the mission of \u003Cem\u003Emaking AI systems explainable and responsible so that people who are not at the table do not end up on the menu\u003C\/em\u003E.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EHuman-centered Explainable AI\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Human-centered Explainable AI "}],"uid":"27707","created_gmt":"2024-10-21 13:59:46","changed_gmt":"2024-10-21 14:00:28","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-10-31T09:30:00-04:00","event_time_end":"2024-10-31T12:30:00-04:00","event_time_end_last":"2024-10-31T12:30:00-04:00","gmt_time_start":"2024-10-31 13:30:00","gmt_time_end":"2024-10-31 16:30:00","gmt_time_end_last":"2024-10-31 16:30:00","rrule":null,"timezone":"America\/New_York"},"location":"ZOOM","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}