{"id":"https://openalex.org/W4414490788","doi":"https://doi.org/10.18653/v1/2026.findings-acl.176","title":"HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks","display_name":"HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414490788","doi":"https://doi.org/10.18653/v1/2026.findings-acl.176"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.176","pdf_url":"https://aclanthology.org/2026.findings-acl.176.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.176.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100457637","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0001-5004-8975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088632705","display_name":"Yusheng Liao","orcid":"https://orcid.org/0000-0001-7549-3944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusheng Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382800","display_name":"Zhiyuan Zhu","orcid":"https://orcid.org/0000-0002-7131-0116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haolin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haolin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010034474","display_name":"H. Li","orcid":"https://orcid.org/0009-0003-3393-1549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongcheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645710","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-8623-1111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626680","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-8344-1586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wang","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":42.387,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99346097,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3592","last_page":"3613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9422000050544739,"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":0.9422000050544739,"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":0.9305999875068665,"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/credibility","display_name":"Credibility","score":0.5198000073432922},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5083000063896179},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5006999969482422},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.3637999892234802},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35420000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814300000667572},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49559998512268066},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.176","pdf_url":"https://aclanthology.org/2026.findings-acl.176.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.12778","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.12778","pdf_url":"https://arxiv.org/pdf/2508.12778","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,"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.2508.12778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.12778","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.176","pdf_url":"https://aclanthology.org/2026.findings-acl.176.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414490788.pdf","grobid_xml":"https://content.openalex.org/works/W4414490788.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"large":[1],"vision-language":[2],"Models":[3],"(Med-LVLMs)":[4],"have":[5],"shown":[6],"promise":[7],"in":[8,21,145],"clinical":[9,61],"applications":[10],"but":[11],"suffer":[12],"from":[13,115],"factual":[14,153],"inaccuracies":[15],"and":[16,76,103,128,136,155],"unreliable":[17],"outputs,":[18],"posing":[19],"risks":[20],"realworld":[22],"diagnostics.While":[23],"RAG":[24,34],"has":[25],"emerged":[26],"as":[27],"a":[28,85,104],"potential":[29],"solution,":[30],"current":[31],"medical":[32,147],"multimodal":[33,73],"systems":[35],"are":[36],"unable":[37],"to":[38,111,125],"perform":[39],"effective":[40,100],"retrieval":[41,102],"across":[42,133],"heterogeneous":[43,92],"sources.The":[44,94],"irrelevance":[45],"of":[46,52,60,157],"retrieved":[47],"reports":[48],"undermines":[49],"the":[50,58,64],"factuality":[51],"analysis,":[53],"while":[54],"insufficient":[55],"knowledge":[56,93,114,130],"affects":[57],"credibility":[59],"decision-making.To":[62],"bridge":[63],"research":[65],"gap,":[66],"we":[67,82],"construct":[68],"MedAtlas,":[69],"which":[70],"includes":[71],"extensive":[72],"report":[74,101],"repositories":[75],"diverse":[77,112],"text":[78],"corpora.Based":[79],"on":[80],"it,":[81],"present":[83],"HeteroRAG,":[84],"novel":[86],"framework":[87,95],"that":[88,140],"enhances":[89],"Med-LVLMs":[90,158],"through":[91],"introduces":[96],"Modality-specific":[97],"CLIPs":[98],"for":[99,108],"Multi-corpora":[105],"Query":[106],"Generator":[107],"tailoring":[109],"queries":[110],"corpora.Incorporating":[113],"such":[116],"multifaceted":[117],"sources,":[118],"Heterogeneous":[119],"Knowledge":[120],"Preference":[121],"Tuning":[122],"is":[123],"performed":[124],"achieve":[126],"cross-modality":[127],"multi-source":[129],"alignment.Extensive":[131],"experiments":[132],"11":[134],"datasets":[135],"3":[137],"modalities":[138],"demonstrate":[139],"HeteroRAG":[141],"achieves":[142],"state-ofthe-art":[143],"performance":[144],"most":[146],"vision":[148],"language":[149],"benchmarks,":[150],"significantly":[151],"improving":[152],"accuracy":[154],"reliability":[156],"1":[159],".":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}