{"id":"https://openalex.org/W4406259849","doi":"https://doi.org/10.1109/bibm62325.2024.10822624","title":"Towards Instruction-Tuned Verification for Improving Biomedical Information Extraction with Large Language Models","display_name":"Towards Instruction-Tuned Verification for Improving Biomedical Information Extraction with Large Language Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259849","doi":"https://doi.org/10.1109/bibm62325.2024.10822624"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822624","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/A5100364819","display_name":"Jin Li","orcid":"https://orcid.org/0000-0003-0385-8793"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"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"],"is_corresponding":true,"raw_author_name":"Jin Li","raw_affiliation_strings":["Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China","Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613528","display_name":"Rui Yuan","orcid":"https://orcid.org/0000-0002-4149-2350"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Yuan","raw_affiliation_strings":["Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057311321","display_name":"Yu Tian","orcid":"https://orcid.org/0000-0002-6791-8217"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yu Tian","raw_affiliation_strings":["Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023138112","display_name":"Jingsong Li","orcid":"https://orcid.org/0000-0002-1064-637X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingsong Li","raw_affiliation_strings":["Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China","Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science and Technology,School of Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I200845125"]},{"raw_affiliation_string":"Zhejiang University,College of Biomedical Engineering &#x0026; Instrumental Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100364819"],"corresponding_institution_ids":["https://openalex.org/I200845125","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.7974,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88077655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6685","last_page":"6692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9767000079154968,"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":0.9767000079154968,"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":0.9449999928474426,"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":0.9230999946594238,"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/computer-science","display_name":"Computer science","score":0.7801501750946045},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5343365669250488},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46228718757629395},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4185437262058258},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40002313256263733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3393530249595642},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07673439383506775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801501750946045},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5343365669250488},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46228718757629395},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4185437262058258},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40002313256263733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393530249595642},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07673439383506775},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822624","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":[{"score":0.5099999904632568,"display_name":"Quality Education","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":27,"referenced_works":["https://openalex.org/W1850865022","https://openalex.org/W2129767020","https://openalex.org/W2170189740","https://openalex.org/W2768488789","https://openalex.org/W4309674289","https://openalex.org/W4378576258","https://openalex.org/W4384071683","https://openalex.org/W4384561707","https://openalex.org/W4385620388","https://openalex.org/W4388116325","https://openalex.org/W4389518760","https://openalex.org/W4389519928","https://openalex.org/W4391292768","https://openalex.org/W4394845024","https://openalex.org/W4399889932","https://openalex.org/W4402155831","https://openalex.org/W4402667093","https://openalex.org/W4403600564","https://openalex.org/W4404782964","https://openalex.org/W6753222228","https://openalex.org/W6776048684","https://openalex.org/W6796581206","https://openalex.org/W6810738896","https://openalex.org/W6837789219","https://openalex.org/W6851658948","https://openalex.org/W6852418670","https://openalex.org/W6871553294"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W2169518243","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2975617233","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W3204019825","https://openalex.org/W2368651715"],"abstract_inverted_index":{"Biomedical":[0],"information":[1,79,107,240],"extraction,":[2],"including":[3],"tasks":[4],"like":[5,50],"Named":[6],"Entity":[7],"Recognition":[8],"(NER)":[9],"and":[10,33,52,88,92,94,104,122,147,164,190,195],"Relationship":[11],"Extraction":[12],"(RE),":[13],"plays":[14],"a":[15,67],"critical":[16],"role":[17],"in":[18,42,58,106,187,206,215,227,248],"analyzing":[19],"unstructured":[20],"biomedical":[21,59,78,145,181,239],"data,":[22],"facilitating":[23],"more":[24],"accurate":[25,238],"downstream":[26],"applications":[27,247],"such":[28],"as":[29],"clinical":[30,250],"decision":[31],"support":[32],"personalized":[34],"medicine.":[35],"Although":[36],"Large":[37],"Language":[38],"Models":[39],"(LLMs)":[40],"excel":[41],"various":[43],"domains,":[44],"they":[45],"often":[46],"struggle":[47],"with":[48],"issues":[49],"hallucinations":[51],"domain-specific":[53],"inaccuracies,":[54],"limiting":[55],"their":[56],"effectiveness":[57,163,223],"applications.":[60],"To":[61],"tackle":[62],"these":[63],"challenges,":[64],"we":[65,110,183],"propose":[66],"novel":[68],"framework":[69,233],"that":[70,172],"incorporates":[71],"an":[72,112,175],"external":[73,176],"dual-stage":[74],"verifier":[75,82,177],"to":[76,85,156,160,213],"enhance":[77],"extraction.":[80,108],"This":[81],"is":[83],"prompted":[84],"first":[86],"identify":[87],"complete":[89],"missing":[90],"entities":[91],"relations,":[93],"then":[95],"filter":[96],"out":[97],"incorrect":[98],"extractions,":[99],"thereby":[100],"enhancing":[101],"both":[102,120,144,225],"precision":[103],"recall":[105],"Furthermore,":[109,218],"proposed":[111,232],"approach":[113],"for":[114,180,193,237],"constructing":[115],"the":[116,127,162,222,228],"instruction-tuning":[117],"dataset":[118],"using":[119,242],"positive":[121],"negative":[123],"demonstrations,":[124],"which":[125],"improves":[126],"verifier\u2019s":[128],"correction":[129],"capabilities":[130],"through":[131],"Parameter-Efficient":[132],"Fine-Tuning":[133],"(PEFT).":[134],"Our":[135,198],"extensive":[136],"experiments":[137],"on":[138],"three":[139],"public":[140],"benchmark":[141],"datasets":[142],"cover":[143],"NER":[146,194],"RE":[148,196],"tasks,":[149,182],"comparing":[150],"four":[151],"LLMs":[152],"ranging":[153],"from":[154],"7":[155],"175":[157],"billion":[158],"parameters":[159],"validate":[161],"scalability":[165],"of":[166,211,224],"our":[167],"approach.":[168],"The":[169,231],"results":[170],"demonstrate":[171,221],"by":[173],"integrating":[174],"specifically":[178],"finetuned":[179],"achieve":[184],"substantial":[185],"improvements":[186],"precision,":[188],"recall,":[189],"F1":[191,207],"scores":[192],"tasks.":[197],"method":[199],"consistently":[200],"outperforms":[201],"In-Context":[202],"Learning":[203],"(ICL)":[204],"approaches":[205],"scores,":[208],"achieving":[209],"increases":[210],"up":[212],"20%":[214],"some":[216],"cases.":[217],"ablation":[219],"studies":[220],"stages":[226],"verification":[229],"process.":[230],"provides":[234],"valuable":[235],"insights":[236],"extraction":[241],"LLMs,":[243],"highlighting":[244],"its":[245],"potential":[246],"real-world":[249],"settings.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
