{"id":"https://openalex.org/W7129502196","doi":"https://doi.org/10.48550/arxiv.2602.13306","title":"Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique","display_name":"Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7129502196","doi":"https://doi.org/10.48550/arxiv.2602.13306"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.13306","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126176202","display_name":"Zhehan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhehan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037583285","display_name":"Meihua Qian","orcid":"https://orcid.org/0000-0002-9383-7939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Meihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126212925","display_name":"Li Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126196523","display_name":"Siyu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126252591","display_name":"Chaoyi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Chaoyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126263942","display_name":"Ripon Saha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saha, Ripon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040888080","display_name":"Xinxin Song","orcid":"https://orcid.org/0000-0003-3868-2644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xinxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17090087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.5892000198364258,"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":0.5892000198364258,"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/T11079","display_name":"Creativity in Education and Neuroscience","score":0.2296999990940094,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.028699999675154686,"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/rubric","display_name":"Rubric","score":0.845300018787384},{"id":"https://openalex.org/keywords/creativity","display_name":"Creativity","score":0.8021000027656555},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.4106999933719635},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.39149999618530273},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.38929998874664307},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3833000063896179},{"id":"https://openalex.org/keywords/computational-creativity","display_name":"Computational creativity","score":0.3617999851703644}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.845300018787384},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48980000615119934},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38190001249313354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32010000944137573},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C70789860","wikidata":"https://www.wikidata.org/wiki/Q2018526","display_name":"The arts","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.13306","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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":"Article"},{"id":"doi:10.48550/arxiv.2602.13306","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13306","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":"pmh:doi:10.48550/arxiv.2602.13306","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Assessing":[0],"artistic":[1],"creativity":[2,6,31,53,215],"is":[3,20,188],"foundational":[4],"to":[5,160,191],"research":[7,216],"and":[8,40,78,104,133,147,174,206,209,217],"arts":[9],"education,":[10],"yet":[11],"manual":[12],"scoring":[13],"(e.g.,":[14],"Torrance":[15],"Tests":[16],"of":[17,55],"Creative":[18],"Thinking)":[19],"labor-intensive":[21],"at":[22],"scale.":[23,181],"Prior":[24],"machine-learning":[25],"approaches":[26],"show":[27,166],"promise":[28],"for":[29,51,214],"visual":[30,122],"scoring,":[32],"but":[33],"many":[34],"rely":[35],"mainly":[36],"on":[37,74,120,178],"image":[38],"features":[39],"provide":[41],"limited":[42],"or":[43,86],"no":[44],"explanatory":[45],"feedback.":[46,219],"We":[47,114],"propose":[48],"a":[49,75,81,96,116,130,138,211],"framework":[50],"automated":[52],"assessment":[54,208],"human":[56],"paintings":[57,72],"by":[58],"fine-tuning":[59],"the":[60,121,126,144,148,152,157,162,179,185],"vision-language":[61],"model":[62,127],"Qwen2-VL-7B":[63],"with":[64,80],"multi-task":[65],"learning.":[66],"Our":[67],"dataset":[68],"contains":[69],"1000":[70],"human-created":[71],"scored":[73],"1-100":[76],"scale":[77],"paired":[79],"short":[82],"human-written":[83],"description":[84,150],"(content":[85],"artist":[87],"explanation).":[88],"Two":[89],"expert":[90,192],"raters":[91],"evaluated":[92],"each":[93],"work":[94],"using":[95],"five-dimension":[97],"rubric":[98,146],"(originality,":[99],"color,":[100],"texture,":[101],"composition,":[102],"content)":[103],"provided":[105],"written":[106],"critiques;":[107],"we":[108,155],"use":[109],"an":[110],"80/20":[111],"train-test":[112],"split.":[113],"add":[115],"lightweight":[117],"regression":[118],"head":[119],"encoder":[123],"output":[124],"so":[125],"can":[128],"predict":[129],"numerical":[131],"score":[132],"generate":[134],"rubric-aligned":[135],"feedback":[136,187],"in":[137,151],"single":[139],"forward":[140],"pass.":[141],"By":[142],"embedding":[143],"structured":[145],"artwork":[149],"system":[153],"prompt,":[154],"constrain":[156],"generated":[158,186],"text":[159],"match":[161],"quantitative":[163],"prediction.":[164],"Experiments":[165],"strong":[167],"accuracy,":[168],"achieving":[169],"Pearson":[170],"r":[171],">":[172],"0.97":[173],"MAE":[175],"about":[176],"3.95":[177],"100-point":[180],"Qualitative":[182],"evaluation":[183],"indicates":[184],"semantically":[189],"close":[190],"critiques":[193],"(average":[194],"SBERT":[195],"cosine":[196],"similarity":[197],"=":[198],"0.798).":[199],"The":[200],"proposed":[201],"approach":[202],"bridges":[203],"computer":[204],"vision":[205],"art":[207],"offers":[210],"scalable":[212],"tool":[213],"classroom":[218]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-18T00:00:00"}