{"id":"https://openalex.org/W7204868477","doi":"https://doi.org/10.48550/arxiv.2608.31139","title":"Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation","display_name":"Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204868477","doi":"https://doi.org/10.48550/arxiv.2608.31139"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31139","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31139","pdf_url":"https://arxiv.org/pdf/2608.31139","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.31139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148845584","display_name":"Riya Ahuja","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahuja, Riya","raw_affiliation_strings":["Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072736528","display_name":"Tim Kacprowski","orcid":"https://orcid.org/0000-0002-5393-2413","observed_orcids":["https://orcid.org/0000-0002-5393-2413"]},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kacprowski, Tim","raw_affiliation_strings":["Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120528895","display_name":"Roya Shiasi Sardoabi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sardoabi, Roya Shiasi","raw_affiliation_strings":["Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.92330002784729,"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":0.92330002784729,"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":0.05920000001788139,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/semantic-chunking","display_name":"semantic chunking","score":0.9610000252723694},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.949999988079071},{"id":"https://openalex.org/keywords/biomedical-information-extraction","display_name":"biomedical information extraction","score":0.7889999747276306},{"id":"https://openalex.org/keywords/biomedical-relation-extraction","display_name":"biomedical relation extraction","score":0.9750000238418579},{"id":"https://openalex.org/keywords/adverse-event-classification","display_name":"adverse event classification","score":0.9399999976158142},{"id":"https://openalex.org/keywords/cross-dataset-generalization","display_name":"cross-dataset generalization","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8644000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788999795913696},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.54830002784729},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4341000020503998},{"id":"https://openalex.org/C2988080768","wikidata":"https://www.wikidata.org/wiki/Q7095057","display_name":"Semantic relation","level":3,"score":0.40209999680519104},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31139","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31139","pdf_url":"https://arxiv.org/pdf/2608.31139","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.31139","doi":"https://doi.org/10.48550/arxiv.2608.31139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31139","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.31139","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31139","pdf_url":"https://arxiv.org/pdf/2608.31139","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160840394","https://openalex.org/W4406320500","https://openalex.org/W7223534785","https://openalex.org/W7126024356","https://openalex.org/W7140327230","https://openalex.org/W2062331696","https://openalex.org/W7164775967","https://openalex.org/W4414304556","https://openalex.org/W7222791666","https://openalex.org/W7214364906"],"abstract_inverted_index":{"BioMedRAG":[0,54],"introduced":[1],"retrieval-augmented":[2],"generation":[3],"with":[4,53,123],"a":[5,26],"learned":[6,67],"chunk":[7,59,68],"scorer":[8],"for":[9,139,171],"biomedical":[10,79,172],"information":[11],"extraction.":[12],"However,":[13],"it":[14],"relies":[15],"on":[16,78],"fixed-size":[17,103,169],"chunking":[18,29,119,134,154,170],"which":[19],"can":[20],"fragment":[21],"semantic":[22,28,118],"evidence.":[23],"We":[24,74],"propose":[25],"configurable":[27],"framework":[30,51,77,160],"that":[31,117],"addresses":[32],"this":[33],"limitation":[34],"by":[35,55,107],"combining":[36],"entity-preserving":[37],"windows,":[38],"trigger-centered":[39],"chunking,":[40],"proposition-first":[41],"extraction,":[42],"tiered":[43],"trigger":[44],"prioritization,":[45],"and":[46,71,86,130,143,150,164],"hierarchical":[47],"relation":[48,80,125],"resolution.":[49],"The":[50],"integrates":[52],"replacing":[56],"only":[57],"the":[58,64,76,93,102,159],"construction":[60],"stage":[61],"while":[62,132],"preserving":[63],"embedding":[65],"model,":[66],"scorer,":[69],"generator,":[70],"evaluation":[72],"protocol.":[73],"evaluate":[75],"extraction":[81,121,142],"benchmarks":[82],"(GM-CIHT,":[83],"DDI,":[84,131],"ChemProt)":[85],"adverse":[87],"event":[88],"classification":[89,145],"(ADE).":[90],"On":[91],"GM-CIHT,":[92],"full":[94],"hybrid":[95],"configuration":[96,157],"achieves":[97],"82.6%":[98],"F1,":[99],"improving":[100],"over":[101],"baseline":[104],"(74.2%":[105],"F1)":[106],"8.4":[108],"points":[109],"under":[110],"our":[111],"experimental":[112],"setup.":[113],"Cross-dataset":[114],"analysis":[115],"shows":[116],"improves":[120],"datasets":[122],"explicit":[124],"cues,":[126],"such":[127,147],"as":[128,148],"GM-CIHT":[129],"fixed":[133],"remains":[135],"competitive":[136],"or":[137],"stronger":[138],"dense":[140],"biochemical":[141],"binary":[144],"settings":[146],"ChemProt":[149],"ADE.":[151],"By":[152],"externalizing":[153],"logic":[155],"into":[156],"files,":[158],"provides":[161],"an":[162],"interpretable":[163],"adaptable":[165],"alternative":[166],"to":[167],"rigid":[168],"RAG":[173],"pipelines.":[174]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}