{"id":"https://openalex.org/W7126091349","doi":"https://doi.org/10.1109/bibm66473.2025.11356825","title":"Task-Adaptive Refined Reinforcement Learning with Granular Reward Shaping for Biomedical Information Extraction","display_name":"Task-Adaptive Refined Reinforcement Learning with Granular Reward Shaping for Biomedical Information Extraction","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126091349","doi":"https://doi.org/10.1109/bibm66473.2025.11356825"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5026705622","display_name":"Qiucheng Miao","orcid":"https://orcid.org/0000-0002-2001-0228"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiucheng Miao","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111465919","display_name":"R. Huang F. L. Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhou","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124216294","display_name":"Jintao Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Meng","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124292028","display_name":"Yanjie Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Wei","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026705622"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8408886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2651","last_page":"2656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.39809998869895935,"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":0.39809998869895935,"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":0.37869998812675476,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.10429999977350235,"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/grasp","display_name":"GRASP","score":0.7771000266075134},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6740999817848206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6729000210762024},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6402000188827515},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6187999844551086},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6075000166893005},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5052000284194946},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4124000072479248}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7771000266075134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6740999817848206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608000159263611},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5052000284194946},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3637000024318695},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.273499995470047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.43644431233406067}],"awards":[{"id":"https://openalex.org/G3138069304","display_name":null,"funder_award_id":"62272449(iPS NSFC),12426303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6093574916","display_name":null,"funder_award_id":"CKL075","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W2970771982","https://openalex.org/W4221153690","https://openalex.org/W4381587418","https://openalex.org/W4390992124","https://openalex.org/W4391836235","https://openalex.org/W4392282268","https://openalex.org/W4396673725","https://openalex.org/W4400111449","https://openalex.org/W4400324908","https://openalex.org/W4401759745","https://openalex.org/W4402669691","https://openalex.org/W4403600564","https://openalex.org/W4404782531","https://openalex.org/W4406259849","https://openalex.org/W4406260660","https://openalex.org/W4406260738","https://openalex.org/W4406261343","https://openalex.org/W4409235391","https://openalex.org/W4411063470","https://openalex.org/W4412654797","https://openalex.org/W4412888533","https://openalex.org/W4416035407"],"related_works":[],"abstract_inverted_index":{"The":[0],"surge":[1],"of":[2,114],"biomedical":[3,52,77,124],"literature":[4],"and":[5,13,58,110,125,137,145,155],"omics":[6],"data":[7],"calls":[8],"for":[9,18,34,76,153],"automated":[10],"knowledge":[11],"extraction,":[12,157],"LLMs":[14,23],"show":[15],"strong":[16],"potential":[17],"this":[19],"task.":[20],"However,":[21],"existing":[22],"still":[24],"struggle":[25],"with":[26,92,140],"structured":[27,115],"tasks,":[28],"as":[29],"they":[30],"are":[31],"primarily":[32],"optimized":[33],"generating":[35],"free-form":[36],"text":[37],"rather":[38],"than":[39],"adhering":[40],"to":[41,49,55,142],"schema-constrained":[42],"outputs.":[43],"LLM":[44],"alignment":[45],"methods":[46],"often":[47],"fail":[48],"generalize":[50],"across":[51,117,123],"tasks":[53],"due":[54],"semantic":[56,138],"ambiguity":[57],"unstable":[59],"policy":[60],"optimization.":[61],"To":[62],"address":[63],"these":[64],"challenges,":[65],"we":[66],"introduce":[67],"GRASP":[68,80,130],"(Group-Relative":[69],"Adaptive":[70],"Structured":[71],"Prompting),":[72],"a":[73,82,93],"unified":[74],"framework":[75],"information":[78],"extraction.":[79],"combines":[81],"hierarchical":[83],"task-aware":[84],"prompt":[85],"design":[86],"that":[87,129],"explicitly":[88],"encodes":[89],"task":[90,108],"semantics":[91],"novel":[94],"Group-Relative":[95],"Policy":[96],"Optimization":[97],"strategy,":[98],"enabling":[99],"fine-grained,":[100],"semantically":[101],"sensitive":[102],"reward":[103],"modeling.":[104],"This":[105],"approach":[106],"resolves":[107],"inter-ference":[109],"enhances":[111],"the":[112],"fidelity":[113],"outputs":[116],"diverse":[118],"extraction":[119],"tasks.":[120],"Extensive":[121],"experiments":[122],"general":[126],"benchmarks":[127],"demonstrate":[128],"achieves":[131],"state-of-the-art":[132],"performance":[133],"in":[134,150],"structural":[135],"accuracy":[136],"consistency,":[139],"up":[141],"11":[143],"%":[144,147],"7":[146],"relative":[148],"improvements":[149],"Micro":[151],"F1":[152],"NER":[154],"relation":[156],"respectively,":[158],"over":[159],"competitive":[160],"baselines.":[161],"Our":[162],"code":[163],"is":[164],"publicly":[165],"available":[166],"at":[167],"GitHub.":[168]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}