{"id":"https://openalex.org/W4404574336","doi":"https://doi.org/10.48550/arxiv.2411.12709","title":"Dimensions of Generative AI Evaluation Design","display_name":"Dimensions of Generative AI Evaluation Design","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404574336","doi":"https://doi.org/10.48550/arxiv.2411.12709"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.12709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.12709","pdf_url":"https://arxiv.org/pdf/2411.12709","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.12709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052688958","display_name":"P. Alex Dow","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dow, P. Alex","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043117896","display_name":"Jennifer Wortman Vaughan","orcid":"https://orcid.org/0000-0002-7807-2018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vaughan, Jennifer Wortman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074825066","display_name":"Solon Barocas","orcid":"https://orcid.org/0000-0003-4577-466X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barocas, Solon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009096729","display_name":"Chad Atalla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atalla, Chad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057438082","display_name":"Alexandra Chouldechova","orcid":"https://orcid.org/0000-0002-2337-9610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chouldechova, Alexandra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wallach, Hanna","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052688958"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.48030000925064087,"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/T12805","display_name":"Cognitive Science and Mapping","score":0.48030000925064087,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7132972478866577},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.6512775421142578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.430037260055542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3231911063194275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2261572778224945},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.08176037669181824}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7132972478866577},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.6512775421142578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.430037260055542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3231911063194275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2261572778224945},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.08176037669181824},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.12709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.12709","pdf_url":"https://arxiv.org/pdf/2411.12709","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.12709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.12709","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.12709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.12709","pdf_url":"https://arxiv.org/pdf/2411.12709","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404574336.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4301024388","https://openalex.org/W775311126","https://openalex.org/W4300030714","https://openalex.org/W4391334978","https://openalex.org/W1517876498","https://openalex.org/W3021262926","https://openalex.org/W3185513875","https://openalex.org/W2489288131","https://openalex.org/W2948893645","https://openalex.org/W178986308"],"abstract_inverted_index":{"There":[0],"are":[1,16],"few":[2],"principles":[3],"or":[4],"guidelines":[5],"to":[6,72],"ensure":[7],"evaluations":[8,66,115],"of":[9,27,91,95,104,107,116],"generative":[10],"AI":[11],"(GenAI)":[12],"models":[13],"and":[14,59,79,111],"systems":[15],"effective.":[17],"To":[18],"help":[19],"address":[20],"this":[21],"gap,":[22],"we":[23,70],"propose":[24],"a":[25,81,101,108],"set":[26,94],"general":[28,96],"dimensions":[29,40,97],"that":[30],"capture":[31],"critical":[32],"choices":[33],"involved":[34],"in":[35],"GenAI":[36,65,76,109,114],"evaluation":[37,43,77,103],"design.":[38],"These":[39],"include":[41],"the":[42,45,48,51,54,56,60,89,92,105],"setting,":[44],"task":[46],"type,":[47,58],"input":[49],"source,":[50],"interaction":[52],"style,":[53],"duration,":[55],"metric":[57],"scoring":[61],"method.":[62],"By":[63],"situating":[64],"within":[67],"these":[68],"dimensions,":[69],"aim":[71],"guide":[73],"decision-making":[74],"during":[75],"design":[78],"provide":[80],"structure":[82],"for":[83],"comparing":[84],"different":[85],"evaluations.":[86],"We":[87],"illustrate":[88],"utility":[90],"proposed":[93],"using":[98],"two":[99],"examples:":[100],"hypothetical":[102],"fairness":[106],"system":[110],"three":[112],"real-world":[113],"biological":[117],"threats.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
