{"id":"https://openalex.org/W7166830882","doi":"https://doi.org/10.18653/v1/2026.acl-long.1718","title":"Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning","display_name":"Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166830882","doi":"https://doi.org/10.18653/v1/2026.acl-long.1718"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1718","pdf_url":"https://aclanthology.org/2026.acl-long.1718.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1718.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139727142","display_name":"Qin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123940","display_name":"Ministry of Education","ror":"https://ror.org/02xv42m49","country_code":"PT","type":"government","lineage":["https://openalex.org/I4210117458","https://openalex.org/I4210123940"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]},{"id":"https://openalex.org/I4210167295","display_name":"Ministry of Energy","ror":"https://ror.org/05rvdw046","country_code":"IL","type":"government","lineage":["https://openalex.org/I4210167295"]}],"countries":["IL","PT","TW"],"is_corresponding":false,"raw_author_name":"Qin Zhou","raw_affiliation_strings":["Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education","institution_ids":["https://openalex.org/I4210123940","https://openalex.org/I4210141165","https://openalex.org/I4210167295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773763","display_name":"Guoyan Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156488","display_name":"Institute of Zoology of the Slovak Academy of Sciences","ror":"https://ror.org/05tm6j853","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210156488"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SK"],"is_corresponding":false,"raw_author_name":"Guoyan Liang","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","institution_ids":["https://openalex.org/I4210156488"]},{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139820575","display_name":"Qianyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156488","display_name":"Institute of Zoology of the Slovak Academy of Sciences","ror":"https://ror.org/05tm6j853","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210156488"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SK"],"is_corresponding":false,"raw_author_name":"Qianyi Yang","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","institution_ids":["https://openalex.org/I4210156488"]},{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139763314","display_name":"Jingyuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156488","display_name":"Institute of Zoology of the Slovak Academy of Sciences","ror":"https://ror.org/05tm6j853","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210156488"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SK"],"is_corresponding":false,"raw_author_name":"Jingyuan Chen","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","institution_ids":["https://openalex.org/I4210156488"]},{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139738875","display_name":"Sai Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156488","display_name":"Institute of Zoology of the Slovak Academy of Sciences","ror":"https://ror.org/05tm6j853","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210156488"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SK"],"is_corresponding":false,"raw_author_name":"Sai Wu","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","institution_ids":["https://openalex.org/I4210156488"]},{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139729982","display_name":"Chang Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156488","display_name":"Institute of Zoology of the Slovak Academy of Sciences","ror":"https://ror.org/05tm6j853","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210156488"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","SK"],"is_corresponding":false,"raw_author_name":"Chang Yao","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","Zhejiang University , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang ) Institute of Blockchain and Data Security","institution_ids":["https://openalex.org/I4210156488"]},{"raw_affiliation_string":"Zhejiang University , Hangzhou , China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139796162","display_name":"Zhe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123940","display_name":"Ministry of Education","ror":"https://ror.org/02xv42m49","country_code":"PT","type":"government","lineage":["https://openalex.org/I4210117458","https://openalex.org/I4210123940"]},{"id":"https://openalex.org/I4210141165","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210141165","https://openalex.org/I4405257903"]},{"id":"https://openalex.org/I4210167295","display_name":"Ministry of Energy","ror":"https://ror.org/05rvdw046","country_code":"IL","type":"government","lineage":["https://openalex.org/I4210167295"]}],"countries":["IL","PT","TW"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Manufacturing in Energy Chemical Process , Ministry of Education","institution_ids":["https://openalex.org/I4210123940","https://openalex.org/I4210141165","https://openalex.org/I4210167295"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"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":0.7957853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37044","last_page":"37056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.26589998602867126,"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":0.26589998602867126,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.19290000200271606,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11739999800920486,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5672000050544739},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43299999833106995},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41200000047683716},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28929999470710754},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.2883000075817108}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5453000068664551},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3107999861240387},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1718","pdf_url":"https://aclanthology.org/2026.acl-long.1718.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1718","pdf_url":"https://aclanthology.org/2026.acl-long.1718.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46292728185653687}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166830882.pdf","grobid_xml":"https://content.openalex.org/works/W7166830882.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"approaches":[4],"have":[5],"advanced":[6],"radiology":[7],"report":[8],"generation":[9],"(RRG),":[10],"yet":[11],"two":[12,49,122],"core":[13],"limitations":[14],"persist:":[15],"(1)":[16],"report-level":[17],"rewards":[18],"offer":[19],"limited":[20],"evidence-grounded":[21],"guidance":[22],"for":[23,65,71,78],"clinical":[24,38],"faithfulness;":[25],"and":[26,74,98,114,130],"(2)":[27],"current":[28],"methods":[29],"lack":[30],"an":[31,100],"explicit":[32],"self-improving":[33],"mechanism":[34],"to":[35,102],"align":[36],"with":[37],"preference.We":[39],"introduce":[40],"clinically":[41,110],"aligned":[42],"Evidence-aware":[43,54],"Self-Correcting":[44],"Reinforcement":[45],"Learning":[46,84],"(ESC-RL),":[47],"comprising":[48],"key":[50],"components.First,":[51],"a":[52,81,89],"Group-wise":[53],"Alignment":[55],"Reward":[56],"(GEAR)":[57],"delivers":[58],"group-wise,":[59],"evidence-aware":[60],"feedback.GEAR":[61],"reinforces":[62],"consistent":[63,128],"grounding":[64],"true":[66],"positives,":[67],"recovers":[68],"missed":[69],"findings":[70],"false":[72,79],"negatives,":[73],"suppresses":[75],"unsupported":[76],"content":[77],"positives.Second,":[80],"Self-correcting":[82],"Preference":[83],"(SPL)":[85],"strategy":[86],"automatically":[87],"constructs":[88],"reliable,":[90],"disease-aware":[91],"preference":[92],"dataset":[93],"from":[94],"multiple":[95],"noisy":[96],"observations":[97],"leverages":[99],"LLM":[101],"synthesize":[103],"refined":[104],"reports":[105],"without":[106],"human":[107],"supervision.ESC-RL":[108],"promotes":[109],"faithful,":[111],"disease-aligned":[112],"reward":[113],"supports":[115],"continual":[116],"self-improvement":[117],"during":[118],"training.Extensive":[119],"experiments":[120],"on":[121],"public":[123],"chest":[124],"X-ray":[125],"datasets":[126],"demonstrate":[127],"gains":[129],"state-of-the-art":[131],"performance.":[132]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}