{"id":"https://openalex.org/W4417529804","doi":"https://doi.org/10.48550/arxiv.2512.16201","title":"Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation","display_name":"Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W4417529804","doi":"https://doi.org/10.48550/arxiv.2512.16201"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.16201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16201","pdf_url":"https://arxiv.org/pdf/2512.16201","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.16201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028447856","display_name":"Sarosij Bose","orcid":"https://orcid.org/0000-0003-3014-4796","observed_orcids":["https://orcid.org/0000-0003-3014-4796"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bose, Sarosij","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003002760","display_name":"Ravi K. Rajendran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajendran, Ravi K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046274165","display_name":"Biplob K. Debnath","orcid":"https://orcid.org/0009-0006-6932-0311","observed_orcids":["https://orcid.org/0009-0006-6932-0311"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debnath, Biplob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006022077","display_name":"Konstantinos Karydis","orcid":"https://orcid.org/0000-0002-1144-8260","observed_orcids":["https://orcid.org/0000-0002-1144-8260"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karydis, Konstantinos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004732580","display_name":"Amit K. Roy\u2013Chowdhury","orcid":"https://orcid.org/0000-0001-6690-9725","observed_orcids":["https://orcid.org/0000-0001-6690-9725"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy-Chowdhury, Amit K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042424184","display_name":"Srimat Chakradhar","orcid":"https://orcid.org/0000-0003-3530-3901","observed_orcids":["https://orcid.org/0000-0003-3530-3901"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakradhar, Srimat","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":null,"has_fulltext":false,"cited_by_count":0,"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":0.9980000257492065,"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":0.9980000257492065,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.0,"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/radiology-report-generation","display_name":"radiology report generation","score":0.9769999980926514},{"id":"https://openalex.org/keywords/medical-vision-language-models","display_name":"medical vision-language models","score":0.8799999952316284},{"id":"https://openalex.org/keywords/cross-modal-alignment","display_name":"cross-modal alignment","score":0.8849999904632568},{"id":"https://openalex.org/keywords/image-text-similarity","display_name":"image-text similarity","score":0.6830000281333923},{"id":"https://openalex.org/keywords/textual-reasoning","display_name":"textual reasoning","score":0.609000027179718},{"id":"https://openalex.org/keywords/chest-x-ray","display_name":"chest radiography","score":0.6110000014305115},{"id":"https://openalex.org/keywords/clinical-accuracy","display_name":"clinical accuracy","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5716000199317932},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147999882698059},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26649999618530273},{"id":"https://openalex.org/C2989236134","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Patient care","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.16201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16201","pdf_url":"https://arxiv.org/pdf/2512.16201","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.16201","doi":"https://doi.org/10.48550/arxiv.2512.16201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.16201","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.16201","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.16201","pdf_url":"https://arxiv.org/pdf/2512.16201","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.428600013256073,"display_name":"Good health and well-being"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Radiology":[0,97],"Report":[1,98],"Generation":[2],"(RRG)":[3],"is":[4],"a":[5,44,139],"critical":[6],"step":[7],"toward":[8,166],"automating":[9],"healthcare":[10],"workflows,":[11],"facilitating":[12],"accurate":[13,42],"patient":[14],"assessments,":[15],"and":[16,40,79,121,153],"reducing":[17],"the":[18,115,149,164],"workload":[19],"of":[20,91],"medical":[21,132,206],"professionals.":[22],"Despite":[23],"recent":[24],"progress":[25],"in":[26],"Large":[27],"Medical":[28,92],"Vision-Language":[29,93],"Models":[30,94],"(Med-VLMs),":[31],"generating":[32],"radiology":[33],"reports":[34,129],"that":[35,161,185],"are":[36,197],"both":[37],"visually":[38,167,198],"grounded":[39,168],"clinically":[41],"remains":[43],"significant":[45,201],"challenge.":[46],"Existing":[47],"approaches":[48],"often":[49],"rely":[50],"on":[51,181],"large":[52],"labeled":[53],"corpora":[54],"for":[55,95],"pre-training,":[56],"costly":[57],"task-specific":[58],"preference":[59,172],"data,":[60],"or":[61,176],"retrieval-based":[62],"knowledge.":[63],"However,":[64],"these":[65,84,157],"strategies":[66],"do":[67],"not":[68],"adequately":[69],"mitigate":[70],"hallucinations":[71,103],"arising":[72],"from":[73],"poor":[74],"cross-modal":[75],"alignment":[76],"between":[77,148],"visual":[78,102],"linguistic":[80],"representations.":[81],"To":[82],"address":[83],"limitations,":[85],"we":[86],"propose":[87],"VALOR:":[88],"Visual":[89,136],"Alignment":[90],"GrOunded":[96],"Generation,":[99],"which":[100,196],"tackles":[101],"through":[104],"two":[105],"complementary":[106],"reasoning":[107],"stages:":[108],"(1)":[109],"Clinically":[110],"Informed":[111],"Textual":[112],"Reasoning":[113,137],"guides":[114],"model":[116],"with":[117,130],"verifiable":[118],"natural":[119],"language":[120],"clinical":[122,194],"metric":[123],"rewards":[124],"to":[125,143],"produce":[126],"semantically":[127],"complete":[128],"precise":[131],"terminology.":[133],"(2)":[134],"Self-Supervised":[135],"leverages":[138],"frozen":[140],"domain":[141],"expert":[142],"compute":[144],"image-text":[145],"similarity":[146],"scores":[147],"input":[150],"chest":[151],"X-ray":[152],"generated":[154],"candidates,":[155],"converting":[156],"into":[158],"rank-normalized":[159],"advantages":[160],"explicitly":[162],"steer":[163],"policy":[165],"outputs,":[169],"requiring":[170],"no":[171],"pairs,":[173],"retrieval":[174],"databases,":[175],"additional":[177],"annotations.":[178],"Extensive":[179],"experiments":[180],"multiple":[182],"benchmarks":[183],"demonstrate":[184],"VALOR":[186],"substantially":[187],"improves":[188],"generation":[189,208],"quality,":[190],"as":[191,193],"well":[192],"accuracy":[195],"grounded,":[199],"achieving":[200],"performance":[202],"gains":[203],"over":[204],"state-of-the-art":[205],"report":[207],"benchmarks.":[209]},"counts_by_year":[],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2025-12-21T00:00:00"}