{"id":"https://openalex.org/W7138268075","doi":"https://doi.org/10.1609/aaai.v40i9.37680","title":"ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation","display_name":"ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138268075","doi":"https://doi.org/10.1609/aaai.v40i9.37680"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37680","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37680","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37680","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129727776","display_name":"Yunyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunyi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129675027","display_name":"Yingshu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingshu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736326","display_name":"Zhanyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanyu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129709199","display_name":"Xinyu Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741999","display_name":"Lingqiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700933","display_name":"Lei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129649546","display_name":"Luping Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luping Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.53125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7413","last_page":"7421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11894","display_name":"Radiology practices and education","score":0.4187999963760376,"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":0.4187999963760376,"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":0.2662999927997589,"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":0.05900000035762787,"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":0.6039000153541565},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4512999951839447},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.31709998846054077},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.296099990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822999715805054},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6039000153541565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5626000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601000189781189},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37680","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37680","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37680","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37680","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37680","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"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":{"Automated":[0],"radiology":[1],"report":[2,18,55],"generation":[3],"(R2Gen)":[4],"has":[5],"advanced":[6],"significantly,":[7],"yet":[8],"evaluation":[9],"remains":[10],"challenging":[11],"due":[12],"to":[13,28,78],"the":[14],"complexity":[15],"of":[16],"assessing":[17],"quality.":[19],"Traditional":[20],"metrics":[21,113],"often":[22],"misalign":[23],"with":[24,72,108],"human":[25,109],"judgments,":[26,110],"failing":[27],"identify":[29],"specific":[30],"deficiencies.":[31],"To":[32],"address":[33],"this,":[34],"we":[35,67],"introduce":[36],"ReFINE,":[37],"a":[38,46,83],"framework":[39],"for":[40],"training":[41,70],"an":[42,95],"Evaluation":[43],"Model":[44],"using":[45],"novel":[47],"margin-based":[48],"reward":[49],"enforcement":[50],"loss.":[51],"This":[52],"approach":[53],"decomposes":[54],"quality":[56,97],"into":[57],"fine-grained":[58],"sub-scores":[59,93],"across":[60,121],"user-defined":[61],"criteria,":[62],"improving":[63],"interpretability.":[64],"Leveraging":[65],"GPT-4,":[66],"generate":[68],"diverse":[69],"data":[71],"paired":[73],"accepted":[74],"and":[75,94,127],"rejected":[76],"reports":[77,129],"train":[79],"our":[80],"model":[81,115],"under":[82,134],"reward-based":[84],"system.":[85],"The":[86],"trained":[87],"ReFINE":[88],"Score":[89],"provides":[90],"both":[91],"granular":[92],"aggregated":[96],"assessment,":[98],"enabling":[99],"criterion-specific":[100],"evaluation.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"ReFINE's":[105],"superior":[106],"alignment":[107],"outperforming":[111],"traditional":[112],"in":[114],"selection.":[116],"Its":[117],"robustness":[118],"is":[119],"validated":[120],"three":[122],"expert-annotated":[123],"datasets\u2014including":[124],"chest":[125],"X-rays":[126],"multimodal":[128],"covering":[130],"9":[131],"imaging":[132],"modalities\u2014and":[133],"two":[135],"distinct":[136],"scoring":[137],"systems.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}