{"id":37,"date":"2021-04-03T16:24:33","date_gmt":"2021-04-03T16:24:33","guid":{"rendered":"https:\/\/aitoolkit.test\/guideline\/mitigate-social-biases\/"},"modified":"2023-05-24T19:39:06","modified_gmt":"2023-05-25T02:39:06","slug":"mitigate-social-biases","status":"publish","type":"guideline","link":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/","title":{"rendered":"Mitigate social biases"},"content":{"rendered":"<div class=\"toolkit-heading-with-image-block\">\n\t\n\n<h2 class=\"wp-block-heading\">Guideline 6: Mitigate social biases<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"10\" src=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png\" alt=\"red header bar\" class=\"wp-image-8820\" srcset=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png 1024w, https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-300x3.png 300w, https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-768x8.png 768w, https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1536x16.png 1536w, https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-2048x21.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading h4\" id=\"do\">Ensure the AI system&#8217;s language and behaviors don&#8217;t reinforce undesirable and unfair stereotypes and biases.<\/h2>\n\n\n\n<p>Societal biases work their ways into AI systems through multiple routes, including with how data is collected, how models are trained and tested, what assumptions are made about the people who will interact with or be impacted by the AI, and more.&nbsp;<\/p>\n\n\n\n<p>Use Guideline 6 as a reminder to plan for identifying, testing, and mitigating fairness harms.&nbsp;&nbsp;<\/p>\n\n\n\n<p>Tools such as&nbsp;<a href=\"https:\/\/erroranalysis.ai\/\" target=\"_blank\" rel=\"noreferrer noopener\">Error Analysis<\/a>&nbsp;and&nbsp;<a href=\"https:\/\/fairlearn.org\/\" target=\"_blank\" rel=\"noreferrer noopener\">Fairlearn<\/a>&nbsp;can help you identify and investigate performance disparities across groups.&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Ensure the AI system\u2019s language and behaviors do not reinforce undesirable and unfair stereotypes and biases.<\/p>\n","protected":false},"menu_order":6,"template":"","meta":{"toolkit_pattern_number":"","ep_exclude_from_search":false,"footnotes":""},"application-type":[68,61,57,96,60,99,56,55,69,29,58,30,59],"goal":[117],"guideline-term":[8],"product-category":[71,70,23,64,62,26,66,28,65,31,32,63],"class_list":["post-37","guideline","type-guideline","status-publish","hentry","application-type-classification","application-type-facial-recognition","application-type-filtering-and-ranking","application-type-gen-ai","application-type-image-recognition","application-type-llm","application-type-natural-language-processing-text","application-type-natural-language-processing-voice","application-type-prediction","application-type-recommendation","application-type-route-planning","application-type-search","application-type-text-generation","goal-fairness","guideline-term-mitigate-social-biases","product-category-advertising","product-category-chatbot","product-category-e-commerce","product-category-email","product-category-health-and-wellness","product-category-navigation","product-category-media-entertainment","product-category-productivity","product-category-search-engine","product-category-social-networks","product-category-voice-assistants","product-category-writing-and-editing"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.8.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Mitigate social biases - Microsoft HAX Toolkit<\/title>\n<meta name=\"description\" content=\"Human-AI Interaction Guideline No. 6: Mitigate social biases. Ensure the AI system&#039;s language and behaviors don&#039;t reinforce undesirable and unfair stereotypes and biases.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Human-AI Interaction Guideline No. 6: Mitigate social biases\" \/>\n<meta property=\"og:description\" content=\"Ensure the AI system&#039;s language and behaviors don&#039;t reinforce undesirable and unfair stereotypes and biases.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/\" \/>\n<meta property=\"og:site_name\" content=\"Microsoft HAX Toolkit\" \/>\n<meta property=\"article:modified_time\" content=\"2023-05-25T02:39:06+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/10\/G-6.png\" \/>\n\t<meta property=\"og:image:width\" content=\"298\" \/>\n\t<meta property=\"og:image:height\" content=\"442\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Human-AI Interaction Guideline No. 6: Mitigate social biases\" \/>\n<meta name=\"twitter:description\" content=\"Ensure the AI system&#039;s language and behaviors don&#039;t reinforce undesirable and unfair stereotypes and biases.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/10\/G-6.png\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n\t<meta name=\"twitter:label2\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data2\" content=\"Shipi Dhanorkar\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/\",\"name\":\"Mitigate social biases - Microsoft HAX Toolkit\",\"isPartOf\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png\",\"datePublished\":\"2021-04-03T16:24:33+00:00\",\"dateModified\":\"2023-05-25T02:39:06+00:00\",\"description\":\"Human-AI Interaction Guideline No. 6: Mitigate social biases. Ensure the AI system's language and behaviors don't reinforce undesirable and unfair stereotypes and biases.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png\",\"contentUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Mitigate social biases\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\",\"name\":\"Microsoft HAX Toolkit\",\"description\":\"Collaborative tools to help you create more effective and responsible human-AI experiences\",\"publisher\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization\",\"name\":\"Microsoft Corporation\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png\",\"contentUrl\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png\",\"width\":1536,\"height\":1536,\"caption\":\"Microsoft Corporation\"},\"image\":{\"@id\":\"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Mitigate social biases - Microsoft HAX Toolkit","description":"Human-AI Interaction Guideline No. 6: Mitigate social biases. Ensure the AI system's language and behaviors don't reinforce undesirable and unfair stereotypes and biases.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/","og_locale":"en_US","og_type":"article","og_title":"Human-AI Interaction Guideline No. 6: Mitigate social biases","og_description":"Ensure the AI system's language and behaviors don't reinforce undesirable and unfair stereotypes and biases.","og_url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/","og_site_name":"Microsoft HAX Toolkit","article_modified_time":"2023-05-25T02:39:06+00:00","og_image":[{"width":298,"height":442,"url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/10\/G-6.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_title":"Human-AI Interaction Guideline No. 6: Mitigate social biases","twitter_description":"Ensure the AI system's language and behaviors don't reinforce undesirable and unfair stereotypes and biases.","twitter_image":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2021\/10\/G-6.png","twitter_misc":{"Est. reading time":"1 minute","Written by":"Shipi Dhanorkar"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/","name":"Mitigate social biases - Microsoft HAX Toolkit","isPartOf":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage"},"image":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage"},"thumbnailUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png","datePublished":"2021-04-03T16:24:33+00:00","dateModified":"2023-05-25T02:39:06+00:00","description":"Human-AI Interaction Guideline No. 6: Mitigate social biases. Ensure the AI system's language and behaviors don't reinforce undesirable and unfair stereotypes and biases.","breadcrumb":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#primaryimage","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png","contentUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2023\/05\/red-header-bar-1536x14-5-23-1024x10.png"},{"@type":"BreadcrumbList","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/guideline\/mitigate-social-biases\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/"},{"@type":"ListItem","position":2,"name":"Mitigate social biases"}]},{"@type":"WebSite","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#website","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/","name":"Microsoft HAX Toolkit","description":"Collaborative tools to help you create more effective and responsible human-AI experiences","publisher":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#organization","name":"Microsoft Corporation","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/","url":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png","contentUrl":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/uploads\/prod\/2022\/07\/msft-logo.png","width":1536,"height":1536,"caption":"Microsoft Corporation"},"image":{"@id":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline\/37","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/types\/guideline"}],"version-history":[{"count":9,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline\/37\/revisions"}],"predecessor-version":[{"id":8865,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline\/37\/revisions\/8865"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/media?parent=37"}],"wp:term":[{"taxonomy":"application-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/application-type?post=37"},{"taxonomy":"goal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/goal?post=37"},{"taxonomy":"guideline-term","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/guideline-term?post=37"},{"taxonomy":"product-category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/wp-json\/wp\/v2\/product-category?post=37"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}