{"id":"https://openalex.org/W4412377200","doi":"https://doi.org/10.1145/3726302.3729901","title":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment","display_name":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377200","doi":"https://doi.org/10.1145/3726302.3729901"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729901","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729901","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018477452","display_name":"Andrey Sakhovskiy","orcid":"https://orcid.org/0000-0003-2762-2910"},"institutions":[{"id":"https://openalex.org/I9115533","display_name":"Moscow Polytechnic University","ror":"https://ror.org/03paz2a60","country_code":"RU","type":"education","lineage":["https://openalex.org/I9115533"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Sakhovskiy","raw_affiliation_strings":["Sber AI, Moscow, Russian Federation and Skoltech, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0003-2762-2910","affiliations":[{"raw_affiliation_string":"Sber AI, Moscow, Russian Federation and Skoltech, Moscow, Russian Federation","institution_ids":["https://openalex.org/I9115533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012311258","display_name":"Elena Tutubalina","orcid":"https://orcid.org/0000-0001-7936-0284"},"institutions":[{"id":"https://openalex.org/I4210144352","display_name":"State Research Center of the Russian Federation","ror":"https://ror.org/04qpssw85","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210144352"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Elena Tutubalina","raw_affiliation_strings":["AIRI, Moscow, Russian Federation, Sber AI, Moscow, Russian Federation, and ISP RAS Research Center for Trusted AI, Moscow, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0001-7936-0284","affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russian Federation, Sber AI, Moscow, Russian Federation, and ISP RAS Research Center for Trusted AI, Moscow, Russian Federation","institution_ids":["https://openalex.org/I4210144352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1652,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97612025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1152","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806621789932251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5303951501846313},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4911081790924072},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4870374798774719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4424988627433777},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.41224706172943115},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.22563016414642334},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.08681991696357727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806621789932251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303951501846313},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4911081790924072},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4870374798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424988627433777},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.41224706172943115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.22563016414642334},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.08681991696357727}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3729901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729901","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.07588","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.07588","pdf_url":"https://arxiv.org/pdf/2509.07588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729901","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377200.pdf","grobid_xml":"https://content.openalex.org/works/W4412377200.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2129113459","https://openalex.org/W2159583324","https://openalex.org/W2169099542","https://openalex.org/W2170189740","https://openalex.org/W2346452181","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2895296143","https://openalex.org/W2953356739","https://openalex.org/W2963318430","https://openalex.org/W2964271799","https://openalex.org/W2970482702","https://openalex.org/W2970986510","https://openalex.org/W2998385486","https://openalex.org/W3027879771","https://openalex.org/W3034229721","https://openalex.org/W3037860573","https://openalex.org/W3046375318","https://openalex.org/W3081168214","https://openalex.org/W3090656107","https://openalex.org/W3096403953","https://openalex.org/W3098266846","https://openalex.org/W3114916066","https://openalex.org/W3116070535","https://openalex.org/W3129831491","https://openalex.org/W3138798301","https://openalex.org/W3151929433","https://openalex.org/W3162922479","https://openalex.org/W3164540570","https://openalex.org/W3172335055","https://openalex.org/W3172427031","https://openalex.org/W3175655865","https://openalex.org/W3176175717","https://openalex.org/W3205810519","https://openalex.org/W4205450747","https://openalex.org/W4205923021","https://openalex.org/W4221142212","https://openalex.org/W4221153690","https://openalex.org/W4224863259","https://openalex.org/W4287888135","https://openalex.org/W4288418349","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4360891289","https://openalex.org/W4385155440","https://openalex.org/W4385572149","https://openalex.org/W4386530347","https://openalex.org/W4393147025","https://openalex.org/W4393264365","https://openalex.org/W4396723183","https://openalex.org/W4401042220","https://openalex.org/W4401042773"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W3213549959","https://openalex.org/W3082797515","https://openalex.org/W4210643529","https://openalex.org/W1778552418","https://openalex.org/W2394860946","https://openalex.org/W1519428778","https://openalex.org/W3203715570","https://openalex.org/W2215005193","https://openalex.org/W143910215"],"abstract_inverted_index":{"In":[0,49],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5],"substantial":[6],"progress":[7],"in":[8,44],"using":[9],"pretrained":[10],"Language":[11,59,112],"Models":[12],"(LMs)":[13],"on":[14,136,149,166],"a":[15,63,83,99,150,167],"range":[16,151],"of":[17,24,34,82,91,152,159],"tasks":[18,155],"aimed":[19],"at":[20],"improving":[21],"the":[22,40,79,89,93,96,109,157],"understanding":[23,154],"biomedical":[25,29,45,105,139],"texts.":[26],"Nonetheless,":[27],"existing":[28],"LLMs":[30],"show":[31],"limited":[32],"comprehension":[33],"complex,":[35],"domain-specific":[36],"concept":[37,106],"structures":[38],"and":[39,58,67,87,95,116,144,156],"factual":[41],"information":[42],"encoded":[43],"Knowledge":[46,56],"Graphs":[47],"(KGs).":[48],"this":[50],"work,":[51],"we":[52,103],"propose":[53],"BALI":[54],"(Biomedical":[55],"Graph":[57],"Model":[60],"Ali":[61],"gnment),":[62],"novel":[64],"joint":[65],"LM":[66,74,94],"KG":[68,85,115,119],"pre-training":[69,165],"method":[70,135],"that":[71,132],"augments":[72],"an":[73],"with":[75,163],"external":[76],"knowledge":[77],"by":[78],"simultaneous":[80],"learning":[81],"dedicated":[84],"encoder":[86],"aligning":[88],"representations":[90],"both":[92],"graph.":[97],"For":[98],"given":[100],"textual":[101],"sequence,":[102],"link":[104],"mentions":[107],"to":[108],"Unified":[110],"Medical":[111],"System":[113],"(UMLS)":[114],"utilize":[117],"local":[118],"subgraphs":[120],"as":[121,142],"cross-modal":[122],"positive":[123],"samples":[124],"for":[125],"these":[126],"mentions.":[127],"Our":[128],"empirical":[129],"findings":[130],"indicate":[131],"implementing":[133],"our":[134],"several":[137],"leading":[138],"LMs,":[140],"such":[141],"PubMedBERT":[143],"BioLinkBERT,":[145],"improves":[146],"their":[147],"performance":[148],"language":[153],"quality":[158],"entity":[160],"representations,":[161],"even":[162],"minimal":[164],"small":[168],"alignment":[169],"dataset":[170],"sourced":[171],"from":[172],"PubMed":[173],"scientific":[174],"abstracts.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}