{"id":"https://openalex.org/W4416197032","doi":"https://doi.org/10.3724/2096-7004.di.2025.0047","title":"BHT-RAG: Birch-based Hierarchical Tree RAG in Mass Spectrometry","display_name":"BHT-RAG: Birch-based Hierarchical Tree RAG in Mass Spectrometry","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416197032","doi":"https://doi.org/10.3724/2096-7004.di.2025.0047"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0047","doi":"https://doi.org/10.3724/2096-7004.di.2025.0047","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0047","pdf_url":"https://www.sciengine.com/doi/pdf/20FB099A6A9545E09099A1C41B6E5434","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/20FB099A6A9545E09099A1C41B6E5434","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Feilong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118987531","display_name":"Anhui Jianzhu University","ror":"https://ror.org/0108wjw08","country_code":"CN","type":"education","lineage":["https://openalex.org/I118987531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Wang","raw_affiliation_strings":["Mass Spectrometry Key Technology R&D and Clinical Application of Anhui Province Jointly Constructed Discipline Key Experiments , Hefei 230601 , China","School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mass Spectrometry Key Technology R&D and Clinical Application of Anhui Province Jointly Constructed Discipline Key Experiments , Hefei 230601 , China","institution_ids":[]},{"raw_affiliation_string":"School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China","institution_ids":["https://openalex.org/I118987531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034906558","display_name":"Donghui Shi","orcid":"https://orcid.org/0000-0001-5301-368X","observed_orcids":["https://orcid.org/0000-0001-5301-368X","https://orcid.org/0009-0000-1126-486X","https://orcid.org/0000-0003-3914-9462"]},"institutions":[{"id":"https://openalex.org/I118987531","display_name":"Anhui Jianzhu University","ror":"https://ror.org/0108wjw08","country_code":"CN","type":"education","lineage":["https://openalex.org/I118987531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghui Shi","raw_affiliation_strings":["Mass Spectrometry Key Technology R&D and Clinical Application of Anhui Province Jointly Constructed Discipline Key Experiments , Hefei 230601 , China","School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mass Spectrometry Key Technology R&D and Clinical Application of Anhui Province Jointly Constructed Discipline Key Experiments , Hefei 230601 , China","institution_ids":[]},{"raw_affiliation_string":"School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China","institution_ids":["https://openalex.org/I118987531"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xinyi Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118987531","display_name":"Anhui Jianzhu University","ror":"https://ror.org/0108wjw08","country_code":"CN","type":"education","lineage":["https://openalex.org/I118987531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Cui","raw_affiliation_strings":["School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering Anhui Jianzhu University , Hefei 230601 , China","institution_ids":["https://openalex.org/I118987531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118987531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22810737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20250047","last_page":"20250047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9369999766349792,"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":0.9369999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04390000179409981,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.003700000001117587,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9959999918937683},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"mass spectrometry","score":0.777999997138977},{"id":"https://openalex.org/keywords/birch-clustering","display_name":"BIRCH clustering","score":0.8379999995231628},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.7020000219345093},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.7889999747276306},{"id":"https://openalex.org/keywords/multiple-choice-question-answering","display_name":"multiple-choice question answering","score":0.8100000023841858},{"id":"https://openalex.org/keywords/fill-in-the-blank-task","display_name":"fill-in-the-blank task","score":0.8610000014305115},{"id":"https://openalex.org/keywords/text-summarization","display_name":"text summarization","score":0.4950000047683716},{"id":"https://openalex.org/keywords/document-chunking","display_name":"document chunking","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008999943733215},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5665000081062317},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5386999845504761},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26840001344680786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0047","doi":"https://doi.org/10.3724/2096-7004.di.2025.0047","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0047","pdf_url":"https://www.sciengine.com/doi/pdf/20FB099A6A9545E09099A1C41B6E5434","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0047","doi":"https://doi.org/10.3724/2096-7004.di.2025.0047","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0047","pdf_url":"https://www.sciengine.com/doi/pdf/20FB099A6A9545E09099A1C41B6E5434","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","jufo-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2802578326","display_name":null,"funder_award_id":"IBES2024ZR01","funder_id":"https://openalex.org/F4320329077","funder_display_name":"Anhui Jianzhu University"}],"funders":[{"id":"https://openalex.org/F4320329077","display_name":"Anhui Jianzhu University","ror":"https://ror.org/0108wjw08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416197032.pdf","grobid_xml":"https://content.openalex.org/works/W4416197032.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,55],"manuscript":[1],"presents":[2],"a":[3,51,60,74,190],"Birch-based":[4],"hierarchical":[5,56],"tree":[6],"retrieval-augmented":[7],"generation":[8,53],"method":[9,135],"(BHT-RAG)":[10],"to":[11,81,122,208,227,232],"mitigate":[12],"the":[13,23,32,69,103,117,130,140,157,222,253,256],"limitations":[14],"of":[15,108,168,181,193,255],"information":[16],"retrieval":[17,20,147],"insufficiency":[18],"and":[19,39,46,50,88,99,111,129,133,165,171,178,184,189,220,247],"quality":[21],"in":[22,59,68,156],"RAG":[24,67,77,120,146,244],"(Retrieval-Augmented":[25],"Generation)":[26],"approach":[27],"within":[28],"mass":[29,70,83,118,158],"spectrometry.":[30],"Specifically,":[31],"documents":[33,92],"were":[34,113,136,149,225,237],"initially":[35,114],"divided":[36],"into":[37],"chunks,":[38],"each":[40],"chunk":[41],"was":[42,85],"then":[43],"vectorized,":[44],"clustered,":[45],"summarized":[47],"utilizing":[48],"Birch":[49],"language":[52],"model.":[54],"clustering":[57,109,134,223],"culminated":[58],"recursive,":[61],"tree-structured":[62],"search":[63],"tree.":[64],"To":[65],"evaluate":[66],"spectrometry":[71,119,159],"domain,":[72],"MSeval,":[73],"publicly":[75,242],"available":[76,243],"evaluation":[78],"dataset":[79,121],"specific":[80],"medical":[82],"spectrometry,":[84],"further":[86],"constructed":[87],"released.":[89],"MSeval":[90],"involves":[91],"for":[93],"retrieval,":[94],"question-answer":[95,174],"pairs,":[96],"multiple-choice":[97,187],"questions,":[98],"fill-in-the-blank":[100],"questions.":[101],"In":[102],"experimental":[104,152,234],"section,":[105],"various":[106],"combinations":[107],"methods":[110,148],"generators":[112],"assessed":[115],"using":[116],"gauge":[123],"their":[124],"generalization":[125,202],"across":[126,203],"different":[127],"tasks,":[128],"optimal":[131],"generator":[132,142],"selected.":[137],"Subsequently,":[138],"under":[139],"same":[141],"conditions,":[143],"four":[144],"other":[145,209,241],"compared.":[150],"The":[151],"results":[153,250],"indicate":[154],"that":[155,251],"dataset,":[160],"BHT-RAG":[161,198],"achieves":[162],"BLEU-4,":[163],"ROUGE-L,":[164],"METEOR":[166],"scores":[167,180],"16.7366,":[169],"31.1675,":[170],"40.8344":[172],"on":[173,186,195,239],"tasks;":[175,188],"precision,":[176],"recall,":[177],"F1":[179],"90.19%,":[182],"89.67%,":[183],"89.93%":[185],"maximum":[191],"accuracy":[192],"80.20%":[194],"fill-inthe-blank":[196],"tasks.":[197],"demonstrates":[199],"superior":[200],"model":[201],"all":[204],"three":[205],"tasks":[206],"compared":[207],"models,":[210],"showcasing":[211],"certain":[212],"effectiveness.":[213],"Additionally,":[214],"supplementary":[215],"ablation":[216],"experiments,":[217],"both":[218],"with":[219],"without":[221],"module,":[224],"conducted":[226,238],"validate":[228],"its":[229],"impact.":[230],"Finally,":[231],"maintain":[233],"integrity,":[235],"tests":[236],"two":[240],"datasets,":[245],"Wikieval":[246],"L-eval,":[248],"yielding":[249],"corroborate":[252],"effectiveness":[254],"proposed":[257],"approach.":[258]},"counts_by_year":[],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2025-11-13T00:00:00"}