{"id":"https://openalex.org/W4414359421","doi":"https://doi.org/10.24963/ijcai.2025/853","title":"Localizing Before Answering: A Benchmark for Grounded Medical Visual Question Answering","display_name":"Localizing Before Answering: A Benchmark for Grounded Medical Visual Question Answering","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359421","doi":"https://doi.org/10.24963/ijcai.2025/853"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/853","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/853","pdf_url":"https://www.ijcai.org/proceedings/2025/0853.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0853.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088833260","display_name":"Nguy\u1ec5n Quang D\u0169ng","orcid":"https://orcid.org/0000-0002-4476-6556"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dung Nguyen","raw_affiliation_strings":["Hanoi University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104282191","display_name":"Minh Khoi Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh Khoi Ho","raw_affiliation_strings":["Hanoi University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042375042","display_name":"Haisen Ta","orcid":"https://orcid.org/0000-0003-2728-3656"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huy Ta","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101918597","display_name":"Th\u00e0nh T\u00e2m Nguy\u00ean","orcid":"https://orcid.org/0000-0002-2586-7757"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thanh Tam Nguyen","raw_affiliation_strings":["Griffith University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340152","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0002-1057-1099"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119679337","display_name":"Kumar Rav","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120278","display_name":"SA Health","ror":"https://ror.org/01tg7a346","country_code":"AU","type":"government","lineage":["https://openalex.org/I2800277939","https://openalex.org/I4210120278"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kumar Rav","raw_affiliation_strings":["SA Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SA Health","institution_ids":["https://openalex.org/I4210120278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112957862","display_name":"Quy Duong Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quy Duong Dang","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044642861","display_name":"Satwik Ramchandre","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Satwik Ramchandre","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050488362","display_name":"Son Lam Phung","orcid":"https://orcid.org/0000-0002-3076-0540"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Son Lam Phung","raw_affiliation_strings":["University of Wollongong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wollongong","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103020604","display_name":"Zhibin Liao","orcid":"https://orcid.org/0000-0001-9965-4511"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhibin Liao","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085105499","display_name":"Minh\u2010Son To","orcid":"https://orcid.org/0000-0002-8060-6218"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Minh-Son To","raw_affiliation_strings":["Flinders University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flinders University","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035480544","display_name":"Johan Verjans","orcid":"https://orcid.org/0000-0002-8336-6774"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Johan Verjans","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058485829","display_name":"Phi Le Nguyen","orcid":"https://orcid.org/0000-0001-6547-7641"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phi Le Nguyen","raw_affiliation_strings":["Hanoi University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086523266","display_name":"Vu Minh Hieu Phan","orcid":"https://orcid.org/0000-0003-3861-0296"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vu Minh Hieu Phan","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.403,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83631125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7670","last_page":"7678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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":0.9948999881744385,"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/T13071","display_name":"Digital Storytelling and Education","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9075000286102295,"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/robustness","display_name":"Robustness (evolution)","score":0.6935999989509583},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6819999814033508},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49219998717308044},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.34220001101493835},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3407999873161316},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.30570000410079956},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6983000040054321},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6935999989509583},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6819999814033508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6061000227928162},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/853","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/853","pdf_url":"https://www.ijcai.org/proceedings/2025/0853.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.00744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00744","pdf_url":"https://arxiv.org/pdf/2505.00744","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/853","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/853","pdf_url":"https://www.ijcai.org/proceedings/2025/0853.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359421.pdf","grobid_xml":"https://content.openalex.org/works/W4414359421.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"Large":[1],"Multi-modal":[2],"Models":[3],"(LMMs)":[4],"have":[5],"demonstrated":[6],"remarkable":[7],"capabilities":[8],"in":[9,34,163],"medical":[10,36,164],"data":[11],"interpretation.":[12],"However,":[13],"these":[14],"models":[15],"frequently":[16],"generate":[17],"hallucinations":[18],"contradicting":[19],"source":[20],"evidence,":[21],"particularly":[22],"due":[23],"to":[24,52,58,76,91,127,135],"inadequate":[25],"localization":[26,79],"reasoning.":[27],"This":[28],"work":[29],"reveals":[30],"a":[31,72,100],"critical":[32],"limitation":[33],"current":[35],"LMMs:":[37],"instead":[38],"of":[39,102,131],"analyzing":[40],"relevant":[41],"pathological":[42,112,138],"regions,":[43],"they":[44],"often":[45],"rely":[46],"on":[47,156],"linguistic":[48],"patterns":[49],"or":[50],"attend":[51],"irrelevant":[53],"image":[54],"areas":[55],"when":[56],"responding":[57],"disease-related":[59],"queries.":[60],"To":[61,114],"address":[62],"this,":[63],"we":[64,118],"introduce":[65],"HEAL-MedVQA":[66,84,159],"(Hallucination":[67],"Evaluation":[68],"via":[69],"Localization":[70],"MedVQA),":[71],"comprehensive":[73],"benchmark":[74],"designed":[75],"evaluate":[77],"LMMs'":[78],"abilities":[80],"and":[81,94,98,133,142],"hallucination":[82],"robustness.":[83],"features":[85],"(i)":[86],"two":[87],"innovative":[88],"evaluation":[89],"protocols":[90],"assess":[92],"visual":[93,116],"textual":[95],"shortcut":[96],"learning,":[97],"(ii)":[99],"dataset":[101],"67K":[103],"VQA":[104],"pairs,":[105],"with":[106],"doctor-annotated":[107],"anatomical":[108],"segmentation":[109],"masks":[110],"for":[111],"regions.":[113],"improve":[115],"reasoning,":[117],"propose":[119],"the":[120,157],"Localize-before-Answer":[121],"(LobA)":[122],"framework,":[123],"which":[124],"trains":[125],"LMMs":[126,155],"localize":[128],"target":[129],"regions":[130],"interest":[132],"self-prompt":[134],"emphasize":[136],"segmented":[137],"areas,":[139],"generating":[140],"grounded":[141],"reliable":[143],"answers.":[144],"Experimental":[145],"results":[146],"demonstrate":[147],"that":[148],"our":[149],"approach":[150],"significantly":[151],"outperforms":[152],"state-of-the-art":[153],"biomedical":[154],"challenging":[158],"benchmark,":[160],"advancing":[161],"robustness":[162],"VQA.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
