{"id":"https://openalex.org/W7204223930","doi":"https://doi.org/10.48550/arxiv.2608.23705","title":"The Limits of Automatic Evaluation of Creativity in Large Language Models","display_name":"The Limits of Automatic Evaluation of Creativity in Large Language Models","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204223930","doi":"https://doi.org/10.48550/arxiv.2608.23705"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23705","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23705","pdf_url":"https://arxiv.org/pdf/2608.23705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125643681","display_name":"Alessandro Tutone","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tutone, Alessandro","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Bologna , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062620952","display_name":"Giorgio Franceschelli","orcid":"https://orcid.org/0000-0003-3210-3015","observed_orcids":["https://orcid.org/0000-0003-3210-3015"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franceschelli, Giorgio","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Bologna , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078886343","display_name":"Mirco Musolesi","orcid":"https://orcid.org/0000-0001-9712-4090","observed_orcids":["https://orcid.org/0000-0001-9712-4090"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Musolesi, Mirco","raw_affiliation_strings":["Centre for Artificial Intelligence , Department of Computer Science , University College London , London , United Kingdom","Department of Computer Science and Engineering , University of Bologna , Bologna , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence , Department of Computer Science , University College London , London , United Kingdom","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.6596999764442444,"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/T10028","display_name":"Topic Modeling","score":0.6596999764442444,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.07490000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.062300000339746475,"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/creativity-assessment","display_name":"creativity assessment","score":0.7699999809265137},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9570000171661377},{"id":"https://openalex.org/keywords/automatic-evaluation-metrics","display_name":"automatic evaluation metrics","score":0.7429999709129333},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.8199999928474426},{"id":"https://openalex.org/keywords/short-stories","display_name":"short stories","score":0.6840000152587891},{"id":"https://openalex.org/keywords/ai-generated-text","display_name":"AI-generated text","score":0.7879999876022339},{"id":"https://openalex.org/keywords/creativity-dimensions","display_name":"creativity dimensions","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.7254999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023000240325928},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3882000148296356},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23705","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23705","pdf_url":"https://arxiv.org/pdf/2608.23705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23705","doi":"https://doi.org/10.48550/arxiv.2608.23705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23705","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23705","pdf_url":"https://arxiv.org/pdf/2608.23705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204223930.pdf","grobid_xml":"https://content.openalex.org/works/W7204223930.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4224035735","https://openalex.org/W4390601409","https://openalex.org/W4401306886","https://openalex.org/W4417006854","https://openalex.org/W7154609574"],"related_works":["https://openalex.org/W7154660018","https://openalex.org/W6910718959","https://openalex.org/W4416034206","https://openalex.org/W4404388589","https://openalex.org/W7164318868","https://openalex.org/W4405253819","https://openalex.org/W4413235349","https://openalex.org/W4396833426","https://openalex.org/W4408292186","https://openalex.org/W4409892328"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"capable":[6],"of":[7,41,47,60,106,138,152,159,166],"generating":[8],"text":[9,154],"that":[10,113,131],"challenges":[11],"human":[12,39,45,82,122],"performance":[13],"in":[14,21,145],"domains":[15],"requiring":[16],"creativity,":[17,61],"yet":[18],"evaluating":[19],"creativity":[20,167],"LLM-generated":[22],"content":[23],"remains":[24],"a":[25,89],"significant":[26],"challenge.":[27],"Here,":[28],"we":[29],"investigate":[30],"whether":[31],"current":[32,146],"automatic":[33,79,116,150],"evaluation":[34,151],"methods":[35],"can":[36],"reliably":[37],"capture":[38,135],"judgments":[40,65,123],"creativity.":[42,139],"We":[43],"collect":[44],"evaluations":[46,80],"human-":[48,126],"and":[49,62,70,81,103,127,155,163],"AI-generated":[50,93,128],"short":[51],"stories":[52],"from":[53],"the":[54,101,149,157,161],"WritingPrompts":[55],"dataset":[56],"across":[57,124],"11":[58],"dimensions":[59,137],"compare":[63],"these":[64],"with":[66,121],"automated":[67],"objective":[68],"metrics":[69,117],"LLM-as-a-Judge":[71],"evaluations.":[72],"Our":[73],"experiments":[74],"reveal":[75],"substantial":[76],"misalignment":[77],"between":[78],"assessments.":[83],"In":[84],"particular,":[85],"LLM-based":[86],"judges":[87],"exhibit":[88,118],"systematic":[90],"preference":[91],"for":[92],"stories,":[94,129],"consistently":[95],"favoring":[96],"their":[97],"stylistic":[98],"characteristics":[99],"over":[100],"unpredictability":[102],"other":[104],"qualities":[105],"human-authored":[107],"texts.":[108],"Furthermore,":[109],"correlation":[110],"analyses":[111],"show":[112],"widely":[114],"used":[115],"near-zero":[119],"alignment":[120],"both":[125],"suggesting":[130],"they":[132],"fail":[133],"to":[134,148,168],"important":[136],"These":[140],"findings":[141],"highlight":[142],"fundamental":[143],"limitations":[144],"approaches":[147],"creative":[153],"underscore":[156],"difficulty":[158],"reducing":[160],"multidimensional":[162],"subjective":[164],"nature":[165],"computational":[169],"metrics.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-27T00:00:00"}
