{"id":"https://openalex.org/W4406259619","doi":"https://doi.org/10.1109/bibm62325.2024.10822725","title":"Adapting Large Language Models for Biomedicine though Retrieval-Augmented Generation with Documents Scoring","display_name":"Adapting Large Language Models for Biomedicine though Retrieval-Augmented Generation with Documents Scoring","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259619","doi":"https://doi.org/10.1109/bibm62325.2024.10822725"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yinkui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinkui Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103284688","display_name":"Tianrun Gao","orcid":"https://orcid.org/0009-0002-6063-1034"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrun Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070951602","display_name":"Jiangjiang Zhang","orcid":"https://orcid.org/0000-0002-9647-5101"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangjiang Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079043263","display_name":"Xiaohong Liu","orcid":"https://orcid.org/0000-0002-5420-2391"},"institutions":[{"id":"https://openalex.org/I4210147892","display_name":"CRUK Lung Cancer Centre of Excellence","ror":"https://ror.org/04nm2mq63","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210147892"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaohong Liu","raw_affiliation_strings":["UCL Cancer Institute, University College London,London,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCL Cancer Institute, University College London,London,United Kingdom","institution_ids":["https://openalex.org/I4210147892","https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458577","display_name":"Guangyu Wang","orcid":"https://orcid.org/0000-0003-1312-884X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5770","last_page":"5775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9876999855041504,"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":0.9876999855041504,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9478999972343445,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9039999842643738,"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/biomedicine","display_name":"Biomedicine","score":0.869771420955658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932694554328918},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5693303346633911},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5482634902000427},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5020349025726318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4602922201156616}],"concepts":[{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.869771420955658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932694554328918},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5693303346633911},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5482634902000427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5020349025726318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602922201156616},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2970482702","https://openalex.org/W3129831491","https://openalex.org/W3162922479","https://openalex.org/W4385245566","https://openalex.org/W4385572634","https://openalex.org/W4388409299","https://openalex.org/W4389761608","https://openalex.org/W4394782456","https://openalex.org/W4400128031","https://openalex.org/W4402670290","https://openalex.org/W6777615688","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6810108873","https://openalex.org/W6810738896","https://openalex.org/W6851658948","https://openalex.org/W6854866820","https://openalex.org/W6856223801","https://openalex.org/W6858095362","https://openalex.org/W6859201984","https://openalex.org/W6860710830","https://openalex.org/W6862500282"],"related_works":["https://openalex.org/W2017899917","https://openalex.org/W2080571363","https://openalex.org/W2481322495","https://openalex.org/W2898682754","https://openalex.org/W2889841093","https://openalex.org/W2151082141","https://openalex.org/W2365236913","https://openalex.org/W3194374240","https://openalex.org/W2993861175","https://openalex.org/W3204019825"],"abstract_inverted_index":{"By":[0],"integrating":[1],"the":[2,27,35,43,46,64,86,122,140,146,159,168],"generative":[3],"capabilities":[4],"of":[5,31,170],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"with":[10],"external":[11],"biomedical":[12,24,118,164],"knowledge":[13],"repositories,":[14],"Retrieval-Augmented":[15],"Generation":[16],"(RAG)":[17],"offers":[18],"significant":[19],"potential":[20],"for":[21,124],"addressing":[22],"knowledge-intensive":[23],"tasks,":[25],"enhancing":[26],"precision":[28],"and":[29,68,110],"effectiveness":[30],"clinical":[32],"decision-making.":[33],"However,":[34],"standard":[36],"RAG":[37,58,92],"approach":[38],"fails":[39],"to":[40,52,62,81,120],"fully":[41],"leverage":[42,85],"information":[44,87,147],"within":[45,88,149],"retrieved":[47,89,108,136,150],"documents,":[48,69,109],"which":[49],"can":[50,133],"lead":[51],"incorrect":[53],"response":[54],"generation.":[55],"While":[56],"advanced":[57],"approaches":[59],"empower":[60],"LLMs":[61,83],"understand":[63],"correlation":[65],"between":[66],"queries":[67],"they":[70],"require":[71],"costly":[72],"annotation.":[73],"In":[74],"this":[75],"work,":[76],"we":[77,156],"propose":[78],"a":[79,104,116],"strategy":[80],"help":[82],"better":[84],"documents":[90,137],"in":[91],"system":[93],"while":[94,166],"reducing":[95],"data":[96,171],"acquisition":[97],"costs.":[98],"We":[99],"fine-tuned":[100,131],"an":[101],"LLM":[102],"on":[103,162],"dataset":[105],"comprising":[106],"queries,":[107],"their":[111],"relevance":[112],"scores":[113],"generated":[114],"by":[115],"pre-trained":[117],"re-ranker":[119],"adapt":[121],"model":[123,132],"answering":[125,139],"questions":[126],"from":[127],"reference":[128],"documents.":[129,151],"The":[130],"independently":[134],"score":[135],"before":[138],"question,":[141],"thereby":[142],"more":[143],"effectively":[144],"utilizing":[145],"contained":[148],"Experimental":[152],"results":[153],"shows":[154],"that":[155],"have":[157],"improved":[158],"model\u2019s":[160],"accuracy":[161],"two":[163],"benchmarks":[165],"reduced":[167],"costs":[169],"acquisition.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}