{"id":"https://openalex.org/W4412945643","doi":"https://doi.org/10.18653/v1/2025.acl-long.323","title":"Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search","display_name":"Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945643","doi":"https://doi.org/10.18653/v1/2025.acl-long.323"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.323","doi":"https://doi.org/10.18653/v1/2025.acl-long.323","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.323","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11155","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103748862","display_name":"Linhao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linhao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038022620","display_name":"Xingguang Ji","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingguang Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375495","display_name":"Yahui Liu","orcid":"https://orcid.org/0000-0002-4018-5404","observed_orcids":["https://orcid.org/0000-0002-4018-5404"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yahui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025326122","display_name":"Fanyu Kong","orcid":"https://orcid.org/0000-0002-8802-9996","observed_orcids":["https://orcid.org/0000-0002-8802-9996"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanheng Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101084466","display_name":"Chenxi Sun","orcid":"https://orcid.org/0000-0002-4161-9876","observed_orcids":["https://orcid.org/0000-0002-4161-9876","https://orcid.org/0009-0002-6396-3958"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxi Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058591055","display_name":"J\u00ecngyu\u00e0n Zh\u0101ng","orcid":"https://orcid.org/0000-0002-3250-2094","observed_orcids":["https://orcid.org/0000-0002-3250-2094"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyuan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776513","display_name":"Hongzhi Zhang","orcid":"https://orcid.org/0000-0001-8025-346X","observed_orcids":["https://orcid.org/0000-0001-8025-346X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongzhi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046573363","display_name":"V. W.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V. W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586838","display_name":"Fuzheng Zhang","orcid":"https://orcid.org/0000-0001-6232-8464","observed_orcids":["https://orcid.org/0000-0001-6232-8464"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuzheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055232825","display_name":"Deyi Xiong","orcid":"https://orcid.org/0000-0002-2353-5038","observed_orcids":["https://orcid.org/0000-0002-2353-5038","https://orcid.org/0009-0007-6501-4496"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deyi Xiong","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":0.7464,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71612903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6435","last_page":"6462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9869999885559082},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.921999990940094},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206682801246643},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7995676398277283},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.575553297996521},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5429794788360596},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5253649950027466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241496562957764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3509647250175476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34972554445266724},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11974233388900757},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1094624400138855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.062496960163116455},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.323","doi":"https://doi.org/10.18653/v1/2025.acl-long.323","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.323","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"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"},{"id":"pmh:oai:arXiv.org:2506.11155","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11155","pdf_url":"https://arxiv.org/pdf/2506.11155","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.11155","doi":"https://doi.org/10.48550/arxiv.2506.11155","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.11155","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:2506.11155","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11155","pdf_url":"https://arxiv.org/pdf/2506.11155","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":null,"license_id":null,"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7202372544","https://openalex.org/W4415537847","https://openalex.org/W4414898051","https://openalex.org/W4403345362","https://openalex.org/W7168052901","https://openalex.org/W7153671994","https://openalex.org/W4410987730","https://openalex.org/W4413146669","https://openalex.org/W4403885521","https://openalex.org/W4402467034"],"abstract_inverted_index":{"Video":[0],"captioning":[1,84,125,152],"can":[2,145],"be":[3],"used":[4],"to":[5,63,104],"assess":[6],"the":[7,87,123,150,157,168,173,189],"video":[8,76,91,109,113,124,151],"understanding":[9],"capabilities":[10],"of":[11,33,38,90,120,136,161,179,191],"Multimodal":[12],"Large":[13],"Language":[14],"Models":[15],"(MLLMs).":[16],"However,":[17],"existing":[18],"benchmarks":[19],"and":[20,41,66,133,147,183,195],"evaluation":[21,43,119],"protocols":[22],"suffer":[23],"from":[24],"crucial":[25],"issues,":[26,48],"such":[27,93],"as":[28,94],"inadequate":[29],"or":[30],"homogeneous":[31],"creation":[32],"key":[34,71],"points,":[35],"exorbitant":[36],"cost":[37],"data":[39,196],"creation,":[40],"limited":[42],"scopes.":[44],"To":[45],"address":[46],"these":[47],"we":[49,164],"propose":[50],"an":[51,79,176],"automatic":[52],"framework,":[53],"named":[54],"AutoCaption,":[55],"which":[56,171],"leverages":[57],"Monte":[58],"Carlo":[59],"Tree":[60],"Search":[61],"(MCTS)":[62],"construct":[64],"numerous":[65],"diverse":[67],"descriptive":[68],"sentences":[69],"(\\textit{i.e.},":[70],"points)":[72],"that":[73,143],"thoroughly":[74],"represent":[75],"content":[77],"in":[78],"iterative":[80,83],"way.":[81],"This":[82],"strategy":[85],"enables":[86],"continuous":[88],"enhancement":[89],"details":[92],"actions,":[95],"objects'":[96],"attributes,":[97],"environment":[98],"details,":[99,114],"etc.":[100],"We":[101,127],"apply":[102],"AutoCaption":[103],"curate":[105],"MCTS-VCB,":[106],"a":[107,117],"fine-grained":[108],"caption":[110],"benchmark":[111],"covering":[112],"thereby":[115],"enabling":[116],"comprehensive":[118],"MLLMs":[121,135],"on":[122,139,181,185],"task.":[126],"evaluate":[128,149],"more":[129],"than":[130],"20":[131],"open-":[132],"closed-source":[134],"varying":[137],"sizes":[138],"MCTS-VCB.":[140],"Results":[141],"show":[142],"MCTS-VCB":[144,182],"effectively":[146],"comprehensively":[148],"capability,":[153],"with":[154,167],"Gemini-1.5-Pro":[155],"achieving":[156],"highest":[158],"F1":[159],"score":[160],"71.2.":[162],"Interestingly,":[163],"fine-tune":[165],"InternVL2.5-8B":[166],"AutoCaption-generated":[169],"data,":[170],"helps":[172],"model":[174],"achieve":[175],"overall":[177],"improvement":[178],"25.0%":[180],"16.3%":[184],"DREAM-1K,":[186],"further":[187],"demonstrating":[188],"effectiveness":[190],"AutoCaption.":[192],"The":[193],"code":[194],"are":[197],"available":[198],"at":[199],"https://github.com/tjunlp-lab/MCTS-VCB.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}