{"id":"https://openalex.org/W4416034991","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.214","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","display_name":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034991","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.214"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.214","pdf_url":"https://aclanthology.org/2025.findings-emnlp.214.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: EMNLP 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-emnlp.214.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058729442","display_name":"Sichu Liang","orcid":"https://orcid.org/0009-0009-6798-1118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sichu Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749334","display_name":"Linhai Zhang","orcid":"https://orcid.org/0000-0003-1009-6870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linhai Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674077","display_name":"Hongyu Zhu","orcid":"https://orcid.org/0009-0000-5993-4666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768918","display_name":"Wenwen Wang","orcid":"https://orcid.org/0000-0003-0840-4846"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenwen Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015709853","display_name":"Yulan He","orcid":"https://orcid.org/0000-0003-3948-5845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulan He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007145568","display_name":"Deyu Zhou","orcid":"https://orcid.org/0000-0001-7702-9387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deyu Zhou","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":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4006","last_page":"4033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.784600019454956,"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":0.784600019454956,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06159999966621399,"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"}},{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.027899999171495438,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/question-answering","display_name":"Question answering","score":0.45989999175071716},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.3093999922275543},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.2994999885559082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26809999346733093}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.43529999256134033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43470001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.226500004529953}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.214","pdf_url":"https://aclanthology.org/2025.findings-emnlp.214.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.214","pdf_url":"https://aclanthology.org/2025.findings-emnlp.214.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2577708131","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3537818187","display_name":null,"funder_award_id":"62176053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5188792329","display_name":null,"funder_award_id":"EP/V020579/1","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6382798043","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034991.pdf","grobid_xml":"https://content.openalex.org/works/W4416034991.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"question":[1],"answering":[2],"fundamentally":[3],"relies":[4],"on":[5],"accurate":[6],"clinical":[7,63,141],"knowledge.The":[8],"dominant":[9],"paradigm,":[10],"Retrieval-Augmented":[11],"Generation":[12],"(RAG),":[13],"acquires":[14],"expertise":[15],"conceptual":[16,55,79],"knowledge":[17,41,56,80,133],"from":[18,81],"large-scale":[19],"medical":[20,97,107],"corpus":[21],"to":[22,114],"guide":[23],"general-purpose":[24],"large":[25],"language":[26],"models":[27],"(LLMs)":[28],"in":[29,43,61],"generating":[30],"trustworthy":[31],"answers.However,":[32],"existing":[33],"retrieval":[34,71],"approaches":[35],"often":[36],"overlook":[37],"the":[38,50,87,112,116,126],"patient-specific":[39,131],"factual":[40,77,132],"embedded":[42],"Electronic":[44],"Health":[45],"Records":[46],"(EHRs),":[47],"which":[48],"limits":[49],"contextual":[51],"relevance":[52],"of":[53,128],"retrieved":[54],"and":[57,78,86,140],"hinders":[58],"its":[59],"effectiveness":[60],"vital":[62],"decisionmaking.This":[64],"paper":[65],"introduces":[66],"RGAR,":[67],"a":[68],"recurrence":[69],"generation-augmented":[70],"framework":[72],"that":[73],"synergistically":[74],"retrieves":[75],"both":[76],"dual":[82],"sources":[83],"(i.e.,":[84],"EHRs":[85],"corpus),":[88],"allowing":[89],"mutual":[90],"refinement":[91],"through":[92],"iterative":[93],"interaction.Across":[94],"three":[95],"factual-aware":[96],"QA":[98],"benchmarks,":[99],"RGAR":[100,110],"establishes":[101],"new":[102],"state-of-theart":[103],"performance":[104],"among":[105],"six":[106],"RAG":[108],"systems.Notably,":[109],"enables":[111],"Llama-3.1-8B-Instructmodel":[113],"surpass":[115],"considerably":[117],"larger":[118],"GPT-3.5":[119],"augmented":[120],"with":[121],"traditional":[122],"RAG.Our":[123],"findings":[124],"demonstrate":[125],"benefit":[127],"explicitly":[129],"mining":[130],"during":[134],"retrieval,":[135],"consistently":[136],"improving":[137],"generation":[138],"quality":[139],"relevance.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}