{"id":817687,"date":"2022-02-01T15:06:04","date_gmt":"2022-02-01T23:06:04","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=817687"},"modified":"2023-07-13T14:42:03","modified_gmt":"2023-07-13T21:42:03","slug":"investigations-of-performance-and-bias-in-human-ai-teamwork-in-hiring","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/investigations-of-performance-and-bias-in-human-ai-teamwork-in-hiring\/","title":{"rendered":"Investigations of Performance and Bias in Human-AI Teamwork in Hiring"},"content":{"rendered":"<p>In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model\u2019s predictive performance and bias may transfer to humans in a recommendation-aided decision task. We consider the domain of ML-assisted hiring, where humans\u2014operating in a constrained selection setting\u2014can choose whether they wish to utilize a trained model\u2019s inferences to help select candidates from written biographies. We conduct a large-scale user study leveraging a re-created dataset of real bios from prior work, where humans predict the ground truth occupation of given candidates with and without the help of three different NLP classifiers (random, bag-of-words, and deep neural network). Our results demonstrate that while high-performance models significantly improve human performance in a hybrid setting, some models mitigate hybrid bias while others accentuate it. We examine these findings through the lens of decision conformity and observe that our model architecture choices have an impact on human-AI conformity and bias, motivating the explicit need to assess these complex dynamics prior to deployment.<\/p>\n<p>All data is available for download <a href=\"https:\/\/www.microsoft.com\/en-us\/download\/details.aspx?id=105296\">here<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model\u2019s predictive performance and bias may transfer to humans [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13554],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[263191],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-817687","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-computer-interaction","msr-locale-en_us","msr-field-of-study-ml-assisted-hiring"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2022-2-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/andipeng.com\/publication\/investigations-of-bias-and-performance-in-human-ai-teamwork-hiring\/","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Andi Peng","user_id":38365,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Andi Peng"},{"type":"user_nicename","value":"Besmira Nushi","user_id":36975,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Besmira Nushi"},{"type":"user_nicename","value":"Emre Kiciman","user_id":31739,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Emre Kiciman"},{"type":"user_nicename","value":"Kori Inkpen","user_id":32569,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Kori Inkpen"},{"type":"user_nicename","value":"Ece Kamar","user_id":31710,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ece Kamar"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[809044],"msr_group":[1105932],"msr_project":[],"publication":[],"video":[],"download":[903447],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/817687"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/817687\/revisions"}],"predecessor-version":[{"id":955209,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/817687\/revisions\/955209"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=817687"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=817687"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=817687"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=817687"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=817687"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=817687"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=817687"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=817687"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=817687"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=817687"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=817687"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=817687"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=817687"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=817687"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=817687"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=817687"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}