{"id":"https://openalex.org/W4416156392","doi":"https://doi.org/10.1145/3800645.3812938","title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","display_name":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W4416156392","doi":"https://doi.org/10.1145/3800645.3812938"},"language":null,"primary_location":{"id":"doi:10.1145/3800645.3812938","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800645.3812938","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Designing Interactive Systems Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3800645.3812938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052708520","display_name":"Charlotte Li","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlotte Li","raw_affiliation_strings":["Northwestern University, Evanston, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0004-8914-3717","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, Illinois, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045947831","display_name":"Nick Hagar","orcid":"https://orcid.org/0000-0001-5110-3737"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Hagar","raw_affiliation_strings":["Northwestern University, Evanston, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0001-5110-3737","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, Illinois, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037405070","display_name":"Sachita Nishal","orcid":"https://orcid.org/0000-0001-6192-6091"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachita Nishal","raw_affiliation_strings":["Northwestern University, Evanston, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0001-6192-6091","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, Illinois, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104023893","display_name":"Jeremy Gilbert","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Gilbert","raw_affiliation_strings":["Medill School, Northwestern University, Evanston, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0008-2585-0972","affiliations":[{"raw_affiliation_string":"Medill School, Northwestern University, Evanston, Illinois, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nicholas Diakopoulos","orcid":"https://orcid.org/0000-0001-5005-6123"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Diakopoulos","raw_affiliation_strings":["Northwestern University, Evanston, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0001-5005-6123","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, Illinois, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00152779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1263","last_page":"1281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5741000175476074,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5741000175476074,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.13760000467300415,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.07580000162124634,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8841000199317932},{"id":"https://openalex.org/keywords/journalism","display_name":"Journalism","score":0.6726999878883362},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5048999786376953},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43630000948905945}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8841000199317932},{"id":"https://openalex.org/C119513131","wikidata":"https://www.wikidata.org/wiki/Q11030","display_name":"Journalism","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5084999799728394},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.33489999175071716},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3165999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C2779318504","wikidata":"https://www.wikidata.org/wiki/Q1438035","display_name":"Research design","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3800645.3812938","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800645.3812938","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Designing Interactive Systems Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.05501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05501","pdf_url":"https://arxiv.org/pdf/2511.05501","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2511.05501","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.05501","pdf_url":"https://arxiv.org/pdf/2511.05501","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.05501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05501","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3800645.3812938","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3800645.3812938","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Designing Interactive Systems Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3994556870","display_name":null,"funder_award_id":"GR-2023-67586","funder_id":"https://openalex.org/F4320308835","funder_display_name":"John S. and James L. Knight Foundation"}],"funders":[{"id":"https://openalex.org/F4320308835","display_name":"John S. and James L. Knight Foundation","ror":"https://ror.org/00mn6be63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Benchmarks":[0],"play":[1],"a":[2,55,73,80],"significant":[3],"role":[4],"in":[5,51,72,95,125],"how":[6,14],"technology":[7],"companies":[8],"communicate":[9],"about":[10],"model":[11],"capabilities":[12],"and":[13,16,90,107,156],"researchers":[15],"the":[17,65,77,126],"public":[18],"understand":[19],"generative":[20],"AI":[21,150],"systems.":[22],"However,":[23],"existing":[24],"benchmarks":[25],"have":[26],"been":[27],"criticized":[28],"for":[29,122,137,149,160],"their":[30],"failure":[31],"to":[32,41,59,99,140],"adequately":[33],"capture":[34],"real-world":[35],"usages":[36],"(i.e.":[37,45],"ecological":[38],"validity)":[39],"or":[40],"measure":[42],"underlying":[43],"concepts":[44],"construct":[46],"validity).":[47],"Building":[48],"on":[49],"approaches":[50,121],"HCI,":[52],"we":[53,68],"adopt":[54],"human-centered":[56],"design":[57,78,147],"process":[58],"address":[60],"such":[61],"critiques.":[62],"Working":[63],"within":[64],"journalism":[66,127,138],"domain":[67,161],"engaged":[69],"23":[70],"professionals":[71],"workshop":[74,85],"which":[75],"informed":[76],"of":[79,119],"domain-oriented":[81],"evaluation":[82,100,135],"\u201ccookbook\u201d.":[83],"Our":[84],"findings":[86],"surface":[87],"domain-specific":[88,105],"challenges":[89],"tensions":[91],"faced":[92],"by":[93],"designers":[94],"translating":[96],"specific":[97],"tasks":[98],"constructs,":[101],"aligning":[102],"metrics":[103],"with":[104],"values,":[106],"balancing":[108],"needs":[109],"among":[110],"different":[111],"stakeholders":[112],"when":[113],"constructing":[114],"evaluations.":[115],"Through":[116],"an":[117,134],"instantiation":[118],"design-based":[120],"benchmark":[123],"creation":[124],"domain,":[128],"this":[129],"work":[130],"not":[131],"only":[132],"produces":[133],"structure":[136],"practitioners":[139],"experiment":[141],"with,":[142],"but":[143],"also":[144],"lays":[145],"out":[146],"requirements":[148],"evaluations":[151],"that":[152],"are":[153],"contextualized,":[154],"value-aligned,":[155],"cultivate":[157],"evaluative":[158],"literacy":[159],"end-users.":[162]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-12T00:00:00"}
