{"id":"https://openalex.org/W7138347920","doi":"https://doi.org/10.1609/aaai.v40i29.39666","title":"What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment","display_name":"What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138347920","doi":"https://doi.org/10.1609/aaai.v40i29.39666"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i29.39666","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39666","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39666/43627","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39666/43627","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069299204","display_name":"Rishab Parthasarathy","orcid":"https://orcid.org/0000-0002-8982-9469"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rishab Parthasarathy","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746555","display_name":"Jasmine Collins","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159714","display_name":"Vibrant Data (United States)","ror":"https://ror.org/054dxwf20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasmine Collins","raw_affiliation_strings":["Databricks Mosaic AI Research"],"affiliations":[{"raw_affiliation_string":"Databricks Mosaic AI Research","institution_ids":["https://openalex.org/I4210159714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080560015","display_name":"Cory Stephenson","orcid":"https://orcid.org/0000-0003-0078-6501"},"institutions":[{"id":"https://openalex.org/I4210159714","display_name":"Vibrant Data (United States)","ror":"https://ror.org/054dxwf20","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cory Stephenson","raw_affiliation_strings":["Databricks Mosaic AI Research"],"affiliations":[{"raw_affiliation_string":"Databricks Mosaic AI Research","institution_ids":["https://openalex.org/I4210159714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069299204"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58730159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"29","first_page":"24801","last_page":"24810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.5555999875068665,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.5555999875068665,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.18729999661445618,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/quality","display_name":"Quality (philosophy)","score":0.6600000262260437},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6151000261306763},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5763000249862671},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4546000063419342},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5228999853134155},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4546000063419342},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i29.39666","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39666","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39666/43627","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i29.39666","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39666","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39666/43627","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138347920.pdf","grobid_xml":"https://content.openalex.org/works/W7138347920.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"evaluation":[1],"of":[2,21,35,58,63,90,105,152,165,172],"generative":[3],"text-to-image":[4],"models":[5],"remains":[6],"a":[7,88,149],"challenging":[8],"problem.":[9],"Recent":[10],"works":[11,25],"have":[12],"proposed":[13],"using":[14,93],"multimodal":[15,31,199,216],"LLMs":[16,32,76,200,217],"to":[17,38,46,79,109,160,170,201,203],"judge":[18,162],"the":[19,120,128,163,173],"quality":[20,107,132,142,164,176],"images,":[22],"but":[23],"these":[24,207],"offer":[26],"little":[27],"insight":[28],"into":[29],"how":[30,213],"make":[33,80],"use":[34,99],"concepts":[36],"relevant":[37],"humans,":[39],"such":[40,190],"as":[41,191],"image":[42,83,96,106,131,141,167,175],"style":[43],"or":[44],"composition,":[45],"generate":[47],"their":[48],"overall":[49],"assessment.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,125,138,185],"study":[55,139],"what":[56],"attributes":[57,108,112,133,143,177],"an":[59,166],"image--specifically":[60],"aesthetics,":[61],"lack":[62],"artifacts,":[64],"anatomical":[65,192],"accuracy,":[66,193],"compositional":[67],"correctness,":[68],"object":[69],"adherence,":[70],"and":[71,77,215],"style--are":[72],"important":[73],"for":[74,154,198],"both":[75],"humans":[78,214],"judgments":[81],"on":[82],"quality.":[84],"We":[85,98],"first":[86],"curate":[87],"dataset":[89],"human":[91,117],"preferences":[92],"synthetically":[94],"generated":[95],"pairs.":[97],"inter-task":[100],"correlation":[101],"between":[102,130,212],"each":[103,155],"pair":[104],"understand":[110],"which":[111],"are":[113,134,158,194],"related":[114],"in":[115],"making":[116],"judgments.":[118],"Repeating":[119],"same":[121],"analysis":[122],"with":[123,148,168],"LLMs,":[124],"find":[126,186],"that":[127,187],"relationships":[129],"much":[135,195],"weaker.":[136],"Finally,":[137],"individual":[140],"by":[144],"generating":[145],"synthetic":[146],"datasets":[147],"high":[150,179],"degree":[151],"control":[153],"axis.":[156],"Humans":[157],"able":[159],"easily":[161],"respect":[169],"all":[171],"specific":[174],"(e.g.":[178],"vs.":[180],"low":[181],"aesthetic":[182],"image),":[183],"however":[184],"some":[188],"attributes,":[189],"more":[196],"difficult":[197],"learn":[202],"judge.":[204],"Taken":[205],"together,":[206],"findings":[208],"reveal":[209],"interesting":[210],"differences":[211],"perceive":[218],"images.":[219]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}