{"id":"https://openalex.org/W4416034091","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.733","title":"MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique","display_name":"MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034091","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.733"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.733","pdf_url":"https://aclanthology.org/2025.findings-emnlp.733.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.733.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308485","display_name":"Gailun Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gailun Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055657033","display_name":"Ziyang Luo","orcid":"https://orcid.org/0000-0002-6037-0471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078451082","display_name":"Hongzhan Lin","orcid":"https://orcid.org/0000-0002-4111-8334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongzhan Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101210809","display_name":"Yuchen Tian","orcid":"https://orcid.org/0009-0002-4952-721X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812385","display_name":"Kaixin Li","orcid":"https://orcid.org/0000-0002-6931-4038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065972237","display_name":"Ziyang Gong","orcid":"https://orcid.org/0009-0006-5191-0380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028160889","display_name":"Jianxiong Guo","orcid":"https://orcid.org/0000-0002-0994-3297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianxiong Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020347295","display_name":"Jing Ma","orcid":"https://orcid.org/0000-0001-5848-9775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15686725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13603","last_page":"13630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.36500000953674316,"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/T12031","display_name":"Speech and dialogue systems","score":0.36500000953674316,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.04729999974370003,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.03359999880194664,"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/field","display_name":"Field (mathematics)","score":0.29910001158714294},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2806999981403351},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2745000123977661},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.2727999985218048},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25929999351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4952999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31929999589920044},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.733","pdf_url":"https://aclanthology.org/2025.findings-emnlp.733.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.733","pdf_url":"https://aclanthology.org/2025.findings-emnlp.733.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5381427449","display_name":null,"funder_award_id":"62202055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6661371309","display_name":null,"funder_award_id":"312200502510","funder_id":"https://openalex.org/F4320321432","funder_display_name":"Beijing Normal University"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321432","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034091.pdf","grobid_xml":"https://content.openalex.org/works/W4416034091.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"ability":[1,53],"of":[2,23,54,84,120,127],"critique":[3,22,52,130,150],"is":[4,82,156],"vital":[5],"for":[6,49,113],"models":[7],"to":[8],"self-improve":[9],"and":[10,38,61,67,81,105,122,146,148],"serve":[11,110],"as":[12,111],"reliable":[13],"AI":[14],"assistants.While":[15],"extensively":[16],"studied":[17],"in":[18,34,102],"languageonly":[19],"settings,":[20],"multimodal":[21],"Large":[24],"Multimodal":[25],"Models":[26],"(LMMs)":[27],"remains":[28],"underexplored":[29],"despite":[30],"their":[31],"growing":[32],"capabilities":[33,131],"tasks":[35],"like":[36],"captioning":[37],"visual":[39],"reasoning.In":[40],"this":[41],"work,":[42],"we":[43,91],"introduce":[44],"MM-CRITIC,":[45],"a":[46,124],"holistic":[47],"benchmark":[48],"evaluating":[50],"the":[51,88,118,141],"LMMs":[55,76],"across":[56,152],"multiple":[57,133],"dimensions:":[58],"basic,":[59],"correction,":[60],"comparison.Covering":[62],"8":[63],"main":[64],"task":[65],"types":[66],"over":[68],"500":[69],"tasks,":[70],"MM-CRITIC":[71,121],"collects":[72],"responses":[73,104],"from":[74],"various":[75],"with":[77],"different":[78],"model":[79],"sizes":[80],"composed":[83],"4471":[85],"samples.To":[86],"enhance":[87],"evaluation":[89,153],"reliability,":[90],"integrate":[92],"expert-informed":[93],"ground":[94],"answers":[95],"into":[96],"scoring":[97],"rubrics":[98],"that":[99],"guide":[100],"GPT-4o":[101],"annotating":[103],"generating":[106],"reference":[107],"critiques,":[108],"which":[109],"anchors":[112],"trustworthy":[114],"judgments.Extensive":[115],"experiments":[116],"validate":[117],"effectiveness":[119],"provide":[123],"comprehensive":[125],"assessment":[126],"leading":[128],"LMMs'":[129],"under":[132],"dimensions.Further":[134],"analysis":[135],"reveals":[136],"some":[137],"key":[138],"insights,":[139],"including":[140],"correlation":[142],"between":[143],"response":[144],"quality":[145],"critique,":[147],"varying":[149],"difficulty":[151],"dimensions.Our":[154],"code":[155],"available":[157],"at":[158],"https://github.com/MichealZeng0420/MM-Critic.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}