{"id":"https://openalex.org/W4400024366","doi":"https://doi.org/10.48550/arxiv.2406.16562","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","display_name":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4400024366","doi":"https://doi.org/10.48550/arxiv.2406.16562"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.16562","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16562","pdf_url":"https://arxiv.org/pdf/2406.16562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2406.16562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111532053","display_name":"Zhiyu Tan","orcid":"https://orcid.org/0009-0000-8110-6066","observed_orcids":["https://orcid.org/0009-0000-8110-6066"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Zhiyu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005227650","display_name":"Xiaomeng Yang","orcid":"https://orcid.org/0000-0001-5484-9665","observed_orcids":["https://orcid.org/0000-0001-5484-9665"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaomeng","raw_affiliation_strings":["Shanghai Academy of AI for Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Academy of AI for Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102683356","display_name":"Luozheng Qin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Luozheng","raw_affiliation_strings":["Shanghai Academy of AI for Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Academy of AI for Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058786230","display_name":"Mengping Yang","orcid":"https://orcid.org/0000-0003-1503-9621","observed_orcids":["https://orcid.org/0000-0003-1503-9621"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Mengping","raw_affiliation_strings":["Shanghai Academy of AI for Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Academy of AI for Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439693","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0003-2135-7546","observed_orcids":["https://orcid.org/0000-0003-2135-7546","https://orcid.org/0009-0004-8737-1820"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Cheng","raw_affiliation_strings":["Carnegie Mellon University https :// sais-fuxi "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University https :// sais-fuxi ","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100348686","display_name":"Hao Li","orcid":"https://orcid.org/0000-0003-2769-4842","observed_orcids":["https://orcid.org/0000-0003-2769-4842"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Hao","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"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":18,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7339000105857849,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7339000105857849,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.260699987411499,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.0007999999797903001,"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/text-to-image-generation","display_name":"text-to-image generation","score":0.8389999866485596},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.9980000257492065},{"id":"https://openalex.org/keywords/metric-stability","display_name":"metric stability","score":0.5690000057220459},{"id":"https://openalex.org/keywords/generative-model-evaluation","display_name":"generative model evaluation","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781354546546936},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6054753661155701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5695010423660278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4415225088596344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38601619005203247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34096765518188477}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.16562","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16562","pdf_url":"https://arxiv.org/pdf/2406.16562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.16562","doi":"https://doi.org/10.48550/arxiv.2406.16562","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.16562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.16562","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16562","pdf_url":"https://arxiv.org/pdf/2406.16562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400024366.pdf","grobid_xml":"https://content.openalex.org/works/W4400024366.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1985514943","https://openalex.org/W3094502228","https://openalex.org/W3153469116","https://openalex.org/W3168867926","https://openalex.org/W4224035735","https://openalex.org/W4321473567","https://openalex.org/W4366850747","https://openalex.org/W4379258791","https://openalex.org/W4379918953","https://openalex.org/W4380994608","https://openalex.org/W4383472654","https://openalex.org/W4386066536","https://openalex.org/W4387723654","https://openalex.org/W4388514904","https://openalex.org/W4389115686","https://openalex.org/W4394656839","https://openalex.org/W4395687488","https://openalex.org/W4402727764","https://openalex.org/W4402727885","https://openalex.org/W4403370734","https://openalex.org/W4403760963","https://openalex.org/W7051896053","https://openalex.org/W7108068597","https://openalex.org/W7133220261"],"related_works":["https://openalex.org/W4405783754","https://openalex.org/W4417256829","https://openalex.org/W7133233895","https://openalex.org/W4414198444","https://openalex.org/W7138290439","https://openalex.org/W4417511766","https://openalex.org/W7133223823","https://openalex.org/W7101589608","https://openalex.org/W7127093854","https://openalex.org/W4414828366"],"abstract_inverted_index":{"The":[0],"recent":[1],"advancements":[2],"in":[3,121,158],"text-to-image":[4,130],"generative":[5],"models":[6,132],"have":[7],"been":[8],"remarkable.":[9],"Yet,":[10],"the":[11,23,35,38,59,105,112],"field":[12],"suffers":[13],"from":[14],"a":[15,46,89,122],"lack":[16],"of":[17,25,37,61,91,104],"evaluation":[18,73,124,127],"metrics":[19,31],"that":[20,32,75,134],"accurately":[21],"reflect":[22],"performance":[24],"these":[26],"models,":[27],"particularly":[28],"lacking":[29],"fine-grained":[30,93],"can":[33],"guide":[34],"optimization":[36],"models.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"EvalAlign,":[45],"metric":[47,140],"characterized":[48],"by":[49],"its":[50,154],"accuracy,":[51],"stability,":[52],"and":[53,83,156],"fine":[54],"granularity.":[55],"Our":[56,126],"approach":[57],"leverages":[58],"capabilities":[60],"Multimodal":[62],"Large":[63],"Language":[64],"Models":[65],"(MLLMs)":[66],"pre-trained":[67],"on":[68,77],"extensive":[69],"data.":[70],"We":[71,108],"develop":[72],"protocols":[74],"focus":[76],"two":[78],"key":[79],"dimensions:":[80],"image":[81],"faithfulness":[82],"text-image":[84],"alignment.":[85],"Each":[86],"protocol":[87],"comprises":[88],"set":[90],"detailed,":[92],"instructions":[94],"linked":[95],"to":[96,114],"specific":[97],"scoring":[98,103],"options,":[99],"enabling":[100],"precise":[101],"manual":[102],"generated":[106],"images.":[107],"supervised":[109],"fine-tune":[110],"(SFT)":[111],"MLLM":[113],"align":[115],"with":[116,147],"human":[117,148],"evaluative":[118],"judgments,":[119],"resulting":[120],"robust":[123],"model.":[125],"across":[128],"24":[129],"generation":[131],"demonstrate":[133],"EvalAlign":[135],"not":[136],"only":[137],"provides":[138],"superior":[139],"stability":[141],"but":[142],"also":[143],"aligns":[144],"more":[145],"closely":[146],"preferences":[149],"than":[150],"existing":[151],"metrics,":[152],"confirming":[153],"effectiveness":[155],"utility":[157],"model":[159],"assessment.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-06-26T00:00:00"}