{"id":"https://openalex.org/W4415539998","doi":"https://doi.org/10.1145/3746027.3755697","title":"From Captions to Rewards <scp>(CaReVL):</scp> Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models","display_name":"From Captions to Rewards <scp>(CaReVL):</scp> Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539998","doi":"https://doi.org/10.1145/3746027.3755697"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073609014","display_name":"Muzhi Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muzhi Dai","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6070-8470","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044176278","display_name":"Jiashuo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Sun","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0007-9160-1918","affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693117","display_name":"Zhiyuan Zhao","orcid":"https://orcid.org/0000-0001-7666-4020"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhao","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7666-4020","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shixuan Liu","orcid":"https://orcid.org/0009-0002-6458-5266"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixuan Liu","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6458-5266","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Li","orcid":"https://orcid.org/0009-0000-1860-0379"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1860-0379","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001848378","display_name":"Junyu Gao","orcid":"https://orcid.org/0000-0001-6000-8168"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Gao","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China and Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-6000-8168","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China and Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0019-4197","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4972","last_page":"4981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9907000064849854,"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/T10028","display_name":"Topic Modeling","score":0.9907000064849854,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.640999972820282},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6351000070571899},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5679000020027161},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5407000184059143},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.39980000257492065},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.3637999892234802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6532999873161316},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.640999972820282},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5121999979019165},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2760217853","https://openalex.org/W4214621929","https://openalex.org/W4398249615","https://openalex.org/W4402670713","https://openalex.org/W4402727405","https://openalex.org/W4404783411","https://openalex.org/W4412888596","https://openalex.org/W4413147297"],"related_works":[],"abstract_inverted_index":{"Aligning":[0],"large":[1],"vision-language":[2],"models":[3,66],"(LVLMs)":[4],"with":[5,32],"human":[6,22],"preferences":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,36,78,88,97,113],"the":[12,90,103],"scarcity":[13],"of":[14,63],"fine-grained,":[15],"high-quality,":[16],"and":[17,57,111,131],"multimodal":[18],"preference":[19,49,100],"data":[20,84,94],"without":[21],"annotations.":[23],"Existing":[24],"methods":[25,128],"relying":[26],"on":[27,129],"direct":[28],"distillation":[29],"often":[30],"struggle":[31],"low-confidence":[33,58,93],"data,":[34],"leading":[35],"suboptimal":[37],"performance.":[38],"To":[39],"address":[40],"this,":[41],"we":[42],"propose":[43],"(CaReVL),":[44],"a":[45,61],"novel":[46],"method":[47],"for":[48,118],"reward":[50,68],"modeling":[51],"by":[52],"reliably":[53],"using":[54,102],"both":[55],"high-":[56],"data.":[59,81],"First,":[60],"cluster":[62],"auxiliary":[64],"expert":[65],"(textual":[67],"models)":[69],"innovatively":[70],"leverages":[71],"image":[72],"captions":[73],"as":[74],"weak":[75],"supervision":[76],"signals":[77],"filter":[79],"high-confidence":[80,83],"The":[82],"are":[85,95,108],"then":[86,109],"used":[87,96],"fine-tune":[89],"LVLM.":[91,105],"Second,":[92],"generate":[98],"diverse":[99],"samples":[101,107],"fine-tuned":[104],"These":[106],"scored":[110],"selected":[112],"construct":[114],"reliable":[115],"chosen-rejected":[116],"pairs":[117],"further":[119],"training.":[120],"(CaReVL)":[121],"achieves":[122],"performance":[123],"improvements":[124],"over":[125],"traditional":[126],"distillation-based":[127],"VL-RewardBench":[130],"MLLM-as-a-Judge":[132],"benchmark,":[133],"demonstrating":[134],"its":[135],"effectiveness.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}