{"id":"https://openalex.org/W4406259991","doi":"https://doi.org/10.1109/bibm62325.2024.10822365","title":"Information-Theoretic Domain Adaptative Training of Medicine Language Models with Rigorous Generalization","display_name":"Information-Theoretic Domain Adaptative Training of Medicine Language Models with Rigorous Generalization","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259991","doi":"https://doi.org/10.1109/bibm62325.2024.10822365"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822365","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":"article","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":"https://openalex.org/A5057129668","display_name":"Guiqiang Zhang","orcid":"https://orcid.org/0000-0002-7759-1983"},"institutions":[{"id":"https://openalex.org/I1300757298","display_name":"Heilongjiang University of Science and Technology","ror":"https://ror.org/030xwyx96","country_code":"CN","type":"education","lineage":["https://openalex.org/I1300757298"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guiqiang Zhang","raw_affiliation_strings":["Heilongjiang University of Science and Technology,Heifei,China"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University of Science and Technology,Heifei,China","institution_ids":["https://openalex.org/I1300757298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107935500","display_name":"Haowen Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowen Jiang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695665","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-3410-7856"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing,China","Johns Hopkins University,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Johns Hopkins University,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016050521","display_name":"Daochun Li","orcid":"https://orcid.org/0000-0002-2081-1666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DongJue Li","raw_affiliation_strings":["Dong Guan JiaRong Foreign Language School,DongGuan,China"],"affiliations":[{"raw_affiliation_string":"Dong Guan JiaRong Foreign Language School,DongGuan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652798","display_name":"Yuheng Li","orcid":"https://orcid.org/0000-0001-6082-6398"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yuheng Li","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing,China","Johns Hopkins University,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Johns Hopkins University,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013321017","display_name":"Rong Nie","orcid":"https://orcid.org/0000-0001-8191-4581"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rong Nie","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057129668"],"corresponding_institution_ids":["https://openalex.org/I1300757298"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36154656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4595","last_page":"4602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13161","display_name":"Ideological and Political Education","score":0.5285999774932861,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13161","display_name":"Ideological and Political Education","score":0.5285999774932861,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6725822687149048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.650892972946167},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.554726779460907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011441707611084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45357242226600647},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.42197537422180176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18371671438217163},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15243694186210632}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6725822687149048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.650892972946167},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.554726779460907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011441707611084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45357242226600647},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.42197537422180176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18371671438217163},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15243694186210632},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822365","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2970482702","https://openalex.org/W3162922479","https://openalex.org/W4381930847","https://openalex.org/W4385307867","https://openalex.org/W4389520259","https://openalex.org/W4391940656","https://openalex.org/W4401043001","https://openalex.org/W4402671943","https://openalex.org/W6782879696","https://openalex.org/W6810108873","https://openalex.org/W6850625674","https://openalex.org/W6851658948","https://openalex.org/W6851787984","https://openalex.org/W6852418670","https://openalex.org/W6852870998","https://openalex.org/W6854866820","https://openalex.org/W6855498594","https://openalex.org/W6856085592","https://openalex.org/W6866650448","https://openalex.org/W6869249025"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2057033141","https://openalex.org/W4252103056","https://openalex.org/W2917823318","https://openalex.org/W2917572814","https://openalex.org/W4242858628","https://openalex.org/W2979406678","https://openalex.org/W2915857720","https://openalex.org/W2916715723","https://openalex.org/W3006129753"],"abstract_inverted_index":{"Contemporary":[0],"advancements":[1],"in":[2,24,107],"large":[3],"language":[4],"models":[5],"(LLMs),":[6],"both":[7],"proprietary":[8],"and":[9,54,73,105],"open-source,":[10],"have":[11,68],"demonstrated":[12],"capabilities":[13],"surpassing":[14],"human":[15,58],"performance":[16],"across":[17],"diverse":[18],"general":[19],"domains.":[20],"Nevertheless,":[21],"their":[22],"efficacy":[23],"specialized":[25],"professional":[26],"fields,":[27],"particularly":[28],"medicine,":[29],"remains":[30],"suboptimal":[31],"within":[32],"the":[33,63,96,108],"open-source":[34],"ecosystem.":[35],"To":[36],"address":[37],"these":[38],"limitations,":[39],"we":[40,67],"introduce":[41],"Domain":[42],"Adaptative":[43],"Medicine-LLM":[44],"(DAMe-LLM).":[45],"Our":[46,93],"approach":[47],"encompasses":[48],"continued":[49,78],"pre-training,":[50,79],"supervised":[51],"fine-tuning":[52],"(SFT),":[53],"reinforcement":[55],"learning":[56],"from":[57],"feedback":[59],"(RLHF)":[60],"methodologies.":[61],"In":[62],"development":[64,106],"of":[65,90,110],"DAMe-LLM,":[66],"curated":[69],"an":[70],"extensive":[71],"Chinese":[72],"English":[74],"medical":[75,91],"dataset":[76,85],"for":[77,102],"complemented":[80],"by":[81],"a":[82,87],"high-fidelity":[83],"SFT":[84],"encompassing":[86],"broad":[88],"spectrum":[89],"specialties.":[92],"contribution":[94],"provides":[95],"scientific":[97],"community":[98],"with":[99],"valuable":[100],"resources":[101],"further":[103],"investigation":[104],"domain":[109],"medicine":[111],"artificial":[112],"intelligence.":[113]},"counts_by_year":[],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}
