{"id":"https://openalex.org/W7166564280","doi":"https://doi.org/10.1145/3805689.3812403","title":"Validating and Refining Measurements for Generative AI Evaluation Via Stakeholder Engagement","display_name":"Validating and Refining Measurements for Generative AI Evaluation Via Stakeholder Engagement","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166564280","doi":"https://doi.org/10.1145/3805689.3812403"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3812403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3812403","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010488057","display_name":"Tonya Nguyen","orcid":"https://orcid.org/0000-0002-7262-0247"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tonya Nguyen","raw_affiliation_strings":["Information Science, University of California, Berkeley, Berkeley, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-7262-0247","affiliations":[{"raw_affiliation_string":"Information Science, University of California, Berkeley, Berkeley, California, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022239852","display_name":"Jean Garcia-Gathright","orcid":"https://orcid.org/0009-0001-5550-640X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean Garcia-Gathright","raw_affiliation_strings":["Microsoft Research, New York City, New York, USA"],"raw_orcid":"https://orcid.org/0009-0001-5550-640X","affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, New York, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730238","display_name":"Hannah Washington","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannah Washington","raw_affiliation_strings":["Microsoft Research, New York City, New York, USA"],"raw_orcid":"https://orcid.org/0009-0002-8124-0147","affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, New York, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057438082","display_name":"Alexandra Chouldechova","orcid":"https://orcid.org/0000-0002-2337-9610"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandra Chouldechova","raw_affiliation_strings":["Microsoft Research, New York City, New York, USA, and Abridge AI Inc., New York City, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-2337-9610","affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, New York, USA, and Abridge AI Inc., New York City, New York, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanna Wallach","raw_affiliation_strings":["Microsoft Research, New York City, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-3395-7186","affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, New York, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043117896","display_name":"Jennifer Wortman Vaughan","orcid":"https://orcid.org/0000-0002-7807-2018"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Wortman Vaughan","raw_affiliation_strings":["Microsoft Research, New York City, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-7807-2018","affiliations":[{"raw_affiliation_string":"Microsoft Research, New York City, New York, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6554","last_page":"6586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11330000311136246,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11330000311136246,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.1054999977350235,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14147","display_name":"Innovative Approaches in Technology and Social Development","score":0.026000000536441803,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/stakeholder","display_name":"Stakeholder","score":0.3472999930381775},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.32170000672340393},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3059999942779541},{"id":"https://openalex.org/keywords/stakeholder-engagement","display_name":"Stakeholder engagement","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5303999781608582},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C201305675","wikidata":"https://www.wikidata.org/wiki/Q852998","display_name":"Stakeholder","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2780984029","wikidata":"https://www.wikidata.org/wiki/Q2930198","display_name":"Stakeholder engagement","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2799000144004822},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805689.3812403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805689.3812403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1602977245","https://openalex.org/W2145683959","https://openalex.org/W2170857744","https://openalex.org/W2324568558","https://openalex.org/W2339955350","https://openalex.org/W2942007046","https://openalex.org/W2942448577","https://openalex.org/W2995006168","https://openalex.org/W2995382404","https://openalex.org/W3016970897","https://openalex.org/W3123058965","https://openalex.org/W3144277077","https://openalex.org/W3172415559","https://openalex.org/W4211192987","https://openalex.org/W4292081290","https://openalex.org/W4296405185","https://openalex.org/W4366548588","https://openalex.org/W4378966551","https://openalex.org/W4385894687","https://openalex.org/W4386249234","https://openalex.org/W4388007985","https://openalex.org/W4388717596","https://openalex.org/W4392939433","https://openalex.org/W4394803801","https://openalex.org/W4394822085","https://openalex.org/W4396863502","https://openalex.org/W4397033040","https://openalex.org/W4404172501","https://openalex.org/W4412888682","https://openalex.org/W6910672816","https://openalex.org/W7162127520"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1,55],"systems":[2],"are":[3,112],"notoriously":[4],"difficult":[5],"to":[6,35,44,69,76,83,109,126,204,216,221,238,244],"evaluate,":[7],"in":[8,53,63,139,147,225],"part":[9],"because":[10],"definitions":[11,101],"of":[12,104,115,142,154,171,235],"their":[13],"capabilities,":[14],"behaviors,":[15],"and":[16,25,102,118,128,149,188],"impacts":[17],"can":[18],"be":[19,77,91,202,242],"contested":[20],"across":[21],"use":[22,89],"cases,":[23],"cultures,":[24],"languages.":[26],"To":[27],"address":[28],"this,":[29],"machine":[30],"learning":[31],"researchers":[32],"have":[33],"begun":[34],"draw":[36],"on":[37,211],"measurement":[38,50,66,227],"theory":[39],"from":[40,213],"the":[41,49,60,74,99,140,151,198,226],"social":[42],"sciences":[43],"develop":[45],"systematic":[46],"frameworks":[47],"for":[48,196,219],"tasks":[51],"involved":[52],"generative":[54],"evaluation.":[56],"In":[57,120],"this":[58,121],"tradition,":[59],"first":[61],"step":[62],"tackling":[64],"a":[65,94,105],"task":[67],"is":[68],"precisely":[70],"define":[71],"or":[72,90],"systematize":[73],"concept":[75,153,200],"measured.":[78],"Systematization":[79],"creates":[80],"an":[81],"opportunity":[82],"include":[84],"stakeholders\u2014including":[85],"those":[86],"who":[87],"will":[88],"impacted":[92],"by":[93,157],"system\u2014in":[95],"conceptual":[96,191],"debates":[97],"about":[98],"proposed":[100],"boundaries":[103],"concept,":[106,180],"ultimately":[107],"leading":[108],"measurements":[110],"that":[111,240],"more":[113],"reflective":[114],"stakeholder":[116,133,207],"needs":[117],"values.":[119],"paper,":[122],"we":[123],"explore":[124],"how":[125,197,220],"validate":[127],"refine":[129],"systematized":[130,152,179,199],"concepts":[131],"via":[132],"engagement.":[134],"We":[135,162,193,209],"situate":[136],"our":[137,214],"study":[138,215],"context":[141],"measuring":[143],"erasure,":[144],"engaging":[145],"stakeholders":[146,224],"validating":[148],"refining":[150],"erasure":[155,172,239],"developed":[156],"Corvi":[158,176],"et":[159,177],"al.":[160],"[13].":[161],"conducted":[163],"six":[164],"workshops":[165],"with":[166,175],"23":[167],"participants.":[168],"Participants'":[169],"understandings":[170],"largely":[173],"aligned":[174],"al.'s":[178],"but":[181],"also":[182],"surfaced":[183],"boundary":[184],"tensions":[185],"requiring":[186],"refinement":[187],"gaps":[189],"suggesting":[190],"expansion.":[192],"provide":[194],"suggestions":[195],"could":[201],"refined":[203],"better":[205,222],"reflect":[206,210],"perspectives.":[208],"learnings":[212],"derive":[217],"recommendations":[218],"engage":[223],"process.":[228],"Content":[229],"Warning:":[230],"This":[231],"paper":[232],"includes":[233],"examples":[234],"language":[236],"related":[237],"may":[241],"harmful":[243],"readers.":[245]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-30T00:00:00"}