{"id":"https://openalex.org/W4403579125","doi":"https://doi.org/10.48550/arxiv.2410.13085","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","display_name":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403579125","doi":"https://doi.org/10.48550/arxiv.2410.13085"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13085","pdf_url":"https://arxiv.org/pdf/2410.13085","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.13085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101776868","display_name":"Peng Xia","orcid":"https://orcid.org/0000-0003-3113-7408"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xia, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114172387","display_name":"Kangyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Kangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763206","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-8435-2489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103281554","display_name":"Tianze Wang","orcid":"https://orcid.org/0000-0003-2717-3596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tianze","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510919","display_name":"Weijia Shi","orcid":"https://orcid.org/0000-0003-4474-4434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Weijia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371257","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0002-1846-9945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925774","display_name":"Linjun Zhang","orcid":"https://orcid.org/0000-0002-9436-0773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Linjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, James","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051534896","display_name":"Huaxiu Yao","orcid":"https://orcid.org/0000-0002-8691-9629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Huaxiu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101776868"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8984000086784363,"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":0.8984000086784363,"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/T10028","display_name":"Topic Modeling","score":0.8805999755859375,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8569999933242798,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.486532598733902},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39792516827583313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3692973256111145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33281952142715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.486532598733902},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39792516827583313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3692973256111145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33281952142715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13085","pdf_url":"https://arxiv.org/pdf/2410.13085","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.13085","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.13085","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13085","pdf_url":"https://arxiv.org/pdf/2410.13085","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403579125.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"(AI)":[2],"has":[3,24],"demonstrated":[4],"significant":[5],"potential":[6],"in":[7,10,18,196,208],"healthcare,":[8],"particularly":[9],"disease":[11],"diagnosis":[12],"and":[13,48,66,72,85,98,107,111,146,161,183,204],"treatment":[14],"planning.":[15],"Recent":[16],"progress":[17],"Medical":[19],"Large":[20],"Vision-Language":[21],"Models":[22],"(Med-LVLMs)":[23],"opened":[25],"up":[26],"new":[27],"possibilities":[28],"for":[29],"interactive":[30],"diagnostic":[31],"tools.":[32],"However,":[33,60],"these":[34,58],"models":[35],"often":[36],"suffer":[37],"from":[38],"factual":[39,198],"hallucination,":[40],"which":[41],"can":[42,99,189],"lead":[43],"to":[44,56,94,127],"incorrect":[45],"diagnoses.":[46],"Fine-tuning":[47],"retrieval-augmented":[49],"generation":[50,185],"(RAG)":[51],"have":[52],"emerged":[53],"as":[54],"methods":[55],"address":[57],"issues.":[59],"the":[61,76,109,112,129,156,197],"amount":[62],"of":[63,78,131,194,200],"high-quality":[64],"data":[65,71,74,203],"distribution":[67],"shifts":[68],"between":[69,105,108],"training":[70],"deployment":[73],"limit":[75],"application":[77],"fine-tuning":[79,151],"methods.":[80],"Although":[81],"RAG":[82,123,157],"is":[83],"lightweight":[84],"effective,":[86],"existing":[87],"RAG-based":[88,149],"approaches":[89],"are":[90,206],"not":[91],"sufficiently":[92,159],"general":[93,160],"different":[95],"medical":[96,174,181],"domains":[97],"potentially":[100],"cause":[101],"misalignment":[102],"issues,":[103],"both":[104],"modalities":[106],"model":[110],"ground":[113],"truth.":[114],"In":[115],"this":[116],"paper,":[117],"we":[118],"propose":[119],"a":[120,136,147],"versatile":[121],"multimodal":[122],"system,":[124],"MMed-RAG,":[125],"designed":[126],"enhance":[128],"factuality":[130],"Med-LVLMs.":[132,201],"Our":[133,202],"approach":[134],"introduces":[135],"domain-aware":[137],"retrieval":[138],"mechanism,":[139],"an":[140,191],"adaptive":[141],"retrieved":[142,168],"contexts":[143],"selection":[144],"method,":[145],"provable":[148],"preference":[150],"strategy.":[152],"These":[153],"innovations":[154],"make":[155],"process":[158],"reliable,":[162],"significantly":[163],"improving":[164],"alignment":[165],"when":[166],"introducing":[167],"contexts.":[169],"Experimental":[170],"results":[171],"across":[172],"five":[173],"datasets":[175],"(involving":[176],"radiology,":[177],"ophthalmology,":[178],"pathology)":[179],"on":[180],"VQA":[182],"report":[184],"demonstrate":[186],"that":[187],"MMed-RAG":[188],"achieve":[190],"average":[192],"improvement":[193],"43.8%":[195],"accuracy":[199],"code":[205],"available":[207],"https://github.com/richard-peng-xia/MMed-RAG.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}