To build machine learning systems that are reliable, trustworthy, and fair, we must be able to provide relevant stakeholders with an understanding of how these systems work. We take a human-centered approach to transparency, supporting responsible AI by working to enable all stakeholders\u2014from designers, developers, and data scientists to policy makers and end users\u2014to understand, monitor, and respond to the behavior of AI systems to the extent necessary to achieve their goals\u200b.<\/p>\n","protected":false},"excerpt":{"rendered":"
We take a human-centered approach to transparency, empirically studying how to provide stakeholders of ML systems with the right information to achieve their goals.<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13554],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-721693","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-computer-interaction","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[863790,863979,559482,919089,563964,919095,594775,919101,647379,923313,687102,996246,688662,1030965,815839,815914,851563],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Jennifer Wortman Vaughan","user_id":32235,"people_section":"Section name 0","alias":"jenn"},{"type":"user_nicename","display_name":"Hanna Wallach","user_id":34779,"people_section":"Section name 0","alias":"wallach"},{"type":"user_nicename","display_name":"Q. Vera Liao","user_id":40912,"people_section":"Section name 0","alias":"veraliao"},{"type":"user_nicename","display_name":"Hal Daum\u00e9 III","user_id":36768,"people_section":"Section name 0","alias":"hal3"},{"type":"user_nicename","display_name":"Forough Poursabzi-Sangdeh (SHE\/HER)","user_id":40264,"people_section":"Section name 0","alias":"fpoursabzi"},{"type":"user_nicename","display_name":"David Alvarez-Melis","user_id":38814,"people_section":"Section name 0","alias":"daalvare"},{"type":"user_nicename","display_name":"Harsha Nori","user_id":41461,"people_section":"Section name 0","alias":"hanori"},{"type":"user_nicename","display_name":"Solon Barocas","user_id":36051,"people_section":"Section name 0","alias":"solon"}],"msr_research_lab":[199571,437514],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/721693"}],"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":7,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/721693\/revisions"}],"predecessor-version":[{"id":919128,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/721693\/revisions\/919128"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=721693"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=721693"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=721693"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=721693"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=721693"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}