{"id":"https://openalex.org/W7165638494","doi":"https://doi.org/10.48550/arxiv.2606.21447","title":"Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning","display_name":"Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165638494","doi":"https://doi.org/10.48550/arxiv.2606.21447"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.21447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21447","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.21447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139193766","display_name":"Ling Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139204878","display_name":"Ruinan Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Ruinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139174452","display_name":"Jun Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139194648","display_name":"Hanliang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hanliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139182119","display_name":"Quirin Strotzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Strotzer, Quirin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139211223","display_name":"Rongkai Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Rongkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139179311","display_name":"Yuan Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136963088","display_name":"Luciano Prevedello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prevedello, Luciano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051533773","display_name":"Dufan Wu","orcid":"https://orcid.org/0000-0002-3204-3502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Dufan","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/T11894","display_name":"Radiology practices and education","score":0.26930001378059387,"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"}},"topics":[{"id":"https://openalex.org/T11894","display_name":"Radiology practices and education","score":0.26930001378059387,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.24040000140666962,"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/T10028","display_name":"Topic Modeling","score":0.2092999964952469,"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/recall","display_name":"Recall","score":0.6808000206947327},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5918999910354614},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5275999903678894},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5020999908447266},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.49140000343322754},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48339998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215999960899353},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307000279426575},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.21447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21447","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:10.48550/arxiv.2606.21447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21447","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8088672161102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"radiology":[1],"report":[2,18],"generation":[3,29],"(RRG)":[4],"has":[5],"gained":[6],"increasing":[7],"attention":[8],"because":[9],"it":[10],"can":[11],"reduce":[12],"the":[13,86,98,119,157,180],"heavy":[14],"workload":[15],"of":[16],"clinical":[17,63,89,107,111,116,125],"writing.":[19],"However,":[20],"most":[21],"existing":[22],"methods":[23],"mainly":[24],"optimize":[25],"for":[26,75],"natural":[27],"language":[28,35],"(NLG)":[30],"metrics":[31],"that":[32,140,161],"focus":[33],"on":[34,156],"fluency,":[36],"while":[37,175],"providing":[38,176],"little":[39],"control":[40,82,178],"over":[41,179],"clinically":[42],"important":[43],"factors":[44],"such":[45],"as":[46],"precision":[47,76,90,182],"and":[48,91,150,171],"recall.":[49],"As":[50],"consequence,":[51],"generated":[52],"reports":[53,103],"may":[54],"be":[55],"fluent":[56],"but":[57],"not":[58],"well":[59],"aligned":[60],"with":[61],"different":[62,106],"needs.":[64],"To":[65,109],"address":[66],"this":[67],"challenge,":[68],"we":[69,113,134],"propose":[70],"a":[71,81,115,136],"reinforcement":[72],"learning":[73],"framework":[74],"recall":[77,92,183],"controllable":[78],"RRG,":[79],"where":[80],"parameter":[83],"explicitly":[84],"adjusts":[85],"trade-off":[87],"between":[88],"during":[93],"inference.":[94],"This":[95],"design":[96],"allows":[97],"model":[99],"to":[100,105],"flexibly":[101],"generate":[102],"according":[104],"requirements.":[108],"ensure":[110],"correctness,":[112],"introduce":[114],"reward":[117,148],"into":[118],"training":[120,138,145,152],"objective,":[121],"which":[122],"helps":[123],"improve":[124],"efficacy":[126],"(CE)":[127],"beyond":[128],"standard":[129],"language-based":[130],"optimization.":[131],"In":[132],"addition,":[133],"apply":[135],"group-relative":[137],"strategy":[139],"normalizes":[141],"rewards":[142],"within":[143],"each":[144],"group,":[146],"reducing":[147],"variance":[149],"improving":[151],"stability.":[153],"Extensive":[154],"experiments":[155],"MIMIC-CXR":[158],"dataset":[159],"show":[160],"our":[162],"method":[163],"consistently":[164],"outperforms":[165],"state-of-the-art":[166],"approaches":[167],"in":[168],"both":[169],"NLG":[170],"CE":[172,181],"evaluation":[173],"metrics,":[174],"reliable":[177],"trade-off.":[184]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-24T00:00:00"}