{"id":"https://openalex.org/W4412888113","doi":"https://doi.org/10.18653/v1/2025.findings-acl.909","title":"Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation","display_name":"Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888113","doi":"https://doi.org/10.18653/v1/2025.findings-acl.909"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.909","pdf_url":"https://aclanthology.org/2025.findings-acl.909.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.909.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050965642","display_name":"Yunsoo Kim","orcid":"https://orcid.org/0000-0001-9376-6141"},"institutions":[{"id":"https://openalex.org/I2801187875","display_name":"University College Lahore","ror":"https://ror.org/0572v5y16","country_code":"PK","type":"education","lineage":["https://openalex.org/I2801187875"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Yunsoo Kim","raw_affiliation_strings":["UCL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I2801187875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111207139","display_name":"Jinge Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801187875","display_name":"University College Lahore","ror":"https://ror.org/0572v5y16","country_code":"PK","type":"education","lineage":["https://openalex.org/I2801187875"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Jinge Wu","raw_affiliation_strings":["UCL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I2801187875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503443","display_name":"Su Hwan Kim","orcid":"https://orcid.org/0000-0002-8465-3564"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Su Hwan Kim","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027431178","display_name":"Pardeep Vasudev","orcid":null},"institutions":[{"id":"https://openalex.org/I2801187875","display_name":"University College Lahore","ror":"https://ror.org/0572v5y16","country_code":"PK","type":"education","lineage":["https://openalex.org/I2801187875"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Pardeep Vasudev","raw_affiliation_strings":["UCL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I2801187875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiashu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiashu Shen","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043821806","display_name":"Honghan Wu","orcid":"https://orcid.org/0000-0002-0213-5668"},"institutions":[{"id":"https://openalex.org/I2801187875","display_name":"University College Lahore","ror":"https://ror.org/0572v5y16","country_code":"PK","type":"education","lineage":["https://openalex.org/I2801187875"]},{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB","PK"],"is_corresponding":false,"raw_author_name":"Honghan Wu","raw_affiliation_strings":["UCL","University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL","institution_ids":["https://openalex.org/I2801187875"]},{"raw_affiliation_string":"University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13680219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17680","last_page":"17694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9840999841690063,"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":0.9840999841690063,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9715999960899353,"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"}},{"id":"https://openalex.org/T11894","display_name":"Radiology practices and education","score":0.9574999809265137,"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/bounding-overwatch","display_name":"Bounding overwatch","score":0.6910510063171387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6831586360931396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4702642858028412},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3947424292564392},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.35670068860054016}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6910510063171387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831586360931396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702642858028412},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3947424292564392},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35670068860054016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.909","pdf_url":"https://aclanthology.org/2025.findings-acl.909.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.909","pdf_url":"https://aclanthology.org/2025.findings-acl.909.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888113.pdf","grobid_xml":"https://content.openalex.org/works/W4412888113.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,18,39,99,193],"multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"have":[8],"significantly":[9],"enhanced":[10],"the":[11,67,187],"automation":[12],"of":[13],"medical":[14],"image":[15],"analysis,":[16],"particularly":[17],"generating":[19],"radiology":[20],"reports":[21],"from":[22,30,119],"chest":[23],"X-rays":[24],"(CXR).However,":[25],"these":[26],"models":[27,116],"still":[28],"suffer":[29],"hallucinations":[31],"and":[32,61,88,109,166,171,180],"clinically":[33,153],"significant":[34,93,154],"errors,":[35],"limiting":[36],"their":[37],"reliability":[38],"real-world":[40],"applications.In":[41],"this":[42],"study,":[43],"we":[44],"propose":[45],"Look":[46],"&":[47],"Mark":[48],"(L&M),":[49],"a":[50,96,110,178],"novel":[51],"grounding":[52],"fixation":[53],"strategy":[54],"that":[55,150],"integrates":[56],"radiologist":[57],"eye":[58],"fixations":[59],"(Look)":[60],"bounding":[62],"box":[63],"annotations":[64],"(Mark)":[65],"into":[66],"LLM":[68],"prompting":[69,108],"framework.Unlike":[70],"conventional":[71],"fine-tuning,":[72],"L&M":[73,91,120,151],"leverages":[74],"in-context":[75,123],"learning":[76],"to":[77,106],"achieve":[78],"substantial":[79],"performance":[80,132],"gains":[81],"without":[82],"retraining.When":[83],"evaluated":[84],"across":[85],"multiple":[86],"domainspecific":[87],"general-purpose":[89],"models,":[90,137],"demonstrates":[92],"gains,":[94],"including":[95],"1.2%":[97],"improvement":[98],"overall":[100],"metrics":[101],"(A.AVG)":[102],"for":[103,114,143,183,189],"CXR-LLaVA":[104],"compared":[105],"baseline":[107],"remarkable":[111],"9.2%":[112],"boost":[113],"LLaVA-Med.General-purpose":[115],"also":[117],"benefit":[118],"combined":[121],"with":[122,125],"learning,":[124],"LLaVA-OV":[126],"achieving":[127],"an":[128],"87.3%":[129],"clinical":[130,195],"average":[131,158],"(C.AVG)-the":[133],"highest":[134],"among":[135],"all":[136],"even":[138],"surpassing":[139],"those":[140],"explicitly":[141],"trained":[142],"CXR":[144],"report":[145],"generation.Expert":[146],"evaluations":[147],"further":[148],"confirm":[149],"reduces":[152],"errors":[155,159],"(by":[156],"0.43":[157],"per":[160],"report),":[161],"such":[162],"as":[163,177],"false":[164],"predictions":[165],"omissions,":[167],"enhancing":[168],"both":[169],"accuracy":[170],"reliability.These":[172],"findings":[173],"highlight":[174],"L&M's":[175],"potential":[176],"scalable":[179],"efficient":[181],"solution":[182],"AI-assisted":[184],"radiology,":[185],"paving":[186],"way":[188],"improved":[190],"diagnostic":[191],"workflows":[192],"low-resource":[194],"settings.":[196]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}