{"id":"https://openalex.org/W4412944756","doi":"https://doi.org/10.18653/v1/2025.acl-long.1088","title":"Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark","display_name":"Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944756","doi":"https://doi.org/10.18653/v1/2025.acl-long.1088"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1088","pdf_url":"https://aclanthology.org/2025.acl-long.1088.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1088.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012821978","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9621-450X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115061672","display_name":"Zi-Ao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zi-Ao Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuehao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuehao Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113891245","display_name":"Heyan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048533046","display_name":"Xian-Ling Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91183643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"22340","last_page":"22361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.7659000158309937,"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/T10799","display_name":"Data Visualization and Analytics","score":0.7659000158309937,"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.7487999796867371,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.6712999939918518,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7874205112457275},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7595316171646118},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7065522074699402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458143949508667},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5193865895271301},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5026991367340088},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4425812065601349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4263589382171631},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38013651967048645},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33766302466392517},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08288240432739258},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.05587109923362732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874205112457275},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7595316171646118},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7065522074699402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458143949508667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5193865895271301},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5026991367340088},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4425812065601349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4263589382171631},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38013651967048645},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33766302466392517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08288240432739258},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.05587109923362732},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1088","pdf_url":"https://aclanthology.org/2025.acl-long.1088.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1088","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1088","pdf_url":"https://aclanthology.org/2025.acl-long.1088.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2563629645","display_name":null,"funder_award_id":"U21B2009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6095425281","display_name":null,"funder_award_id":"62276110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8878491478","display_name":null,"funder_award_id":"62172039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944756.pdf","grobid_xml":"https://content.openalex.org/works/W4412944756.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Driven":[0],"by":[1],"the":[2,15,109,185],"remarkable":[3],"progress":[4],"in":[5,75,82,195],"diffusion":[6],"models,":[7],"text-to-image":[8],"generation":[9],"has":[10],"achieved":[11],"substantial":[12],"advancements,":[13],"underscoring":[14],"urgent":[16],"need":[17],"for":[18,173],"robust":[19],"automatic":[20],"quality":[21,85,171],"assessment.This":[22],"task":[23,93],"is":[24],"inherently":[25],"complex,":[26],"requiring":[27],"evaluations":[28],"that":[29,166,178],"range":[30],"from":[31],"object":[32],"presence":[33],"and":[34,40,60,77,116,151,156,197],"attribute":[35],"correctness":[36],"to":[37,100,129,141,149],"relational":[38],"consistency":[39],"visual":[41],"fidelity.Consequently,":[42],"current":[43,186],"state-of-the-art":[44,187],"MLLM-based":[45],"approaches":[46],"often":[47],"rely":[48],"on":[49,98,121],"powerful":[50],"commercial":[51],"models":[52],"such":[53],"as":[54],"GPT-4o,":[55],"which":[56],"offer":[57],"superior":[58],"reasoning":[59],"instruction-following":[61],"capabilities":[62,133],"but":[63],"are":[64],"not":[65],"universally":[66],"accessible.In":[67],"contrast,":[68],"while":[69],"opensource":[70],"MLLMs":[71],"demonstrate":[72,177],"promising":[73],"skills":[74],"vision":[76],"language":[78],"understanding,":[79],"they":[80],"underperform":[81],"comprehensive":[83],"image":[84],"assessment.To":[86],"address":[87],"these":[88],"challenges,":[89],"we":[90,124,160],"propose":[91],"a":[92,103,135,163],"decomposition":[94],"evaluation":[95,111,132],"framework":[96],"based":[97],"GPT-4o":[99],"automatically":[101],"construct":[102],"specialized":[104],"training":[105,127],"dataset,":[106,123],"breaking":[107],"down":[108],"multifaceted":[110],"process":[112],"into":[113,134],"simpler":[114],"sub-tasks":[115],"thus":[117],"reducing":[118],"learning":[119],"complexity.Building":[120],"this":[122],"design":[125],"novel":[126],"strategies":[128],"distill":[130],"GPT-4o's":[131],"7B":[136],"open-source":[137,181],"MLLM,":[138],"MiniCPM-V-2.6,enabling":[139],"it":[140],"better":[142],"follow":[143],"instructions":[144],"across":[145],"diverse":[146],"assessment":[147],"criteria.Furthermore,":[148],"reliably":[150],"comprehensively":[152],"assess":[153],"prior":[154],"works":[155],"our":[157,179],"proposed":[158],"model,":[159],"manually":[161],"annotate":[162],"meta-evaluation":[164],"benchmark":[165],"includes":[167],"chain-of-thought":[168],"explanations":[169],"alongside":[170],"scores":[172],"generated":[174],"images.Experimental":[175],"results":[176],"distilled":[180],"MLLM":[182],"significantly":[183],"outperforms":[184],"GPT-4o-base":[188],"baseline,":[189],"VIEScore,":[190],"with":[191,200],"over":[192],"4.6%":[193],"improvement":[194],"Spearman":[196],"Kendall":[198],"correlations":[199],"human":[201],"judgments.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}