{"id":"https://openalex.org/W4414879438","doi":"https://doi.org/10.48550/arxiv.2507.17234","title":"CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings","display_name":"CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4414879438","doi":"https://doi.org/10.48550/arxiv.2507.17234"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.17234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17234","pdf_url":"https://arxiv.org/pdf/2507.17234","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/2507.17234","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017875448","display_name":"Kyeongkyu Lee","orcid":"https://orcid.org/0009-0009-6318-1244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kyeongkyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yoon, Seonghwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Seonghwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019802439","display_name":"Hongki Lim","orcid":"https://orcid.org/0000-0002-2764-3730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Hongki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9591000080108643,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9591000080108643,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9559000134468079,"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/correctness","display_name":"Correctness","score":0.8478000164031982},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.7559000253677368},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.673799991607666},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5175999999046326},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5130000114440918},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5083000063896179}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8478000164031982},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.7559000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226999998092651},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.673799991607666},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.17234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17234","pdf_url":"https://arxiv.org/pdf/2507.17234","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.17234","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.17234","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:2507.17234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17234","pdf_url":"https://arxiv.org/pdf/2507.17234","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"generation":[1],"of":[2,38,66,95],"radiology":[3],"reports":[4,40],"has":[5],"the":[6,35,39,63,72,91,96,101,112,140,150,161],"potential":[7],"to":[8,17,77],"alleviate":[9],"radiologists'":[10],"significant":[11],"workload,":[12],"yet":[13],"current":[14],"methods":[15],"struggle":[16],"deliver":[18],"clinically":[19],"reliable":[20],"conclusions.":[21],"In":[22],"particular,":[23],"most":[24],"prior":[25],"approaches":[26],"focus":[27],"on":[28,44,160,176],"producing":[29],"fluent":[30],"text":[31],"without":[32],"effectively":[33],"ensuring":[34,138],"factual":[36],"correctness":[37,60],"and":[41,114,152,172],"often":[42],"rely":[43],"single-view":[45],"images,":[46],"limiting":[47],"diagnostic":[48,59],"comprehensiveness.":[49],"We":[50],"propose":[51],"CLARIFID,":[52],"a":[53,122,130,144],"novel":[54],"framework":[55],"that":[56,107,139,165],"directly":[57],"optimizes":[58],"by":[61,135],"mirroring":[62],"two-step":[64],"workflow":[65],"experts.":[67],"Specifically,":[68],"CLARIFID":[69],"(1)":[70],"learns":[71],"logical":[73],"flow":[74],"from":[75],"Findings":[76],"Impression":[78,97],"through":[79],"section-aware":[80],"pretraining,":[81],"(2)":[82],"is":[83],"fine-tuned":[84],"with":[85],"Proximal":[86],"Policy":[87],"Optimization":[88],"in":[89],"which":[90],"CheXbert":[92],"F1":[93],"score":[94],"section":[98,147],"serves":[99],"as":[100],"reward,":[102],"(3)":[103],"employs":[104],"controlled":[105],"decoding":[106],"completes":[108],"\"Findings\"":[109,146],"before":[110,148],"synthesizing":[111,149],"\"Impression\",":[113],"(4)":[115],"fuses":[116],"multiple":[117],"chest":[118],"X-ray":[119],"views":[120],"via":[121],"vision-transformer-based":[123],"multi-view":[124],"encoder.":[125],"During":[126],"inference,":[127],"we":[128],"apply":[129],"next-token":[131],"forcing":[132],"strategy":[133],"followed":[134],"report-level":[136],"re-ranking,":[137],"model":[141],"first":[142],"produces":[143],"comprehensive":[145],"\"Impression\"":[151],"thereby":[153],"preserving":[154],"coherent":[155],"clinical":[156,170,177],"reasoning.":[157],"Experimental":[158],"results":[159],"MIMIC-CXR":[162],"dataset":[163],"demonstrate":[164],"our":[166],"method":[167],"achieves":[168],"superior":[169],"efficacy":[171,178],"outperforms":[173],"existing":[174],"baselines":[175],"scores.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}