{"id":"https://openalex.org/W7203709730","doi":"https://doi.org/10.48550/arxiv.2608.14737","title":"Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews","display_name":"Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203709730","doi":"https://doi.org/10.48550/arxiv.2608.14737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14737","pdf_url":"https://arxiv.org/pdf/2608.14737","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":"review","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128287001","display_name":"Gilberto Sussumu Hida","orcid":"https://orcid.org/0009-0003-2310-5323","observed_orcids":["https://orcid.org/0009-0003-2310-5323"]},"institutions":[{"id":"https://openalex.org/I4210123235","display_name":"Centro de Estudos e Sistemas Avan\u00e7ados do Recife","ror":"https://ror.org/02t7xfd51","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123235"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Hida, Gilberto Sussumu","raw_affiliation_strings":["Cesar School -AIBL Recife - PE - Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cesar School -AIBL Recife - PE - Brazil","institution_ids":["https://openalex.org/I4210123235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843160","display_name":"Danilo Monteiro Ribeiro","orcid":"https://orcid.org/0000-0001-7393-729X","observed_orcids":["https://orcid.org/0000-0001-7393-729X"]},"institutions":[{"id":"https://openalex.org/I4210123235","display_name":"Centro de Estudos e Sistemas Avan\u00e7ados do Recife","ror":"https://ror.org/02t7xfd51","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123235"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ribeiro, Danilo Monteiro","raw_affiliation_strings":["Cesar School -AIBL Recife - PE - Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cesar School -AIBL Recife - PE - Brazil","institution_ids":["https://openalex.org/I4210123235"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006977294","display_name":"Clayton Suguio Hida","orcid":"https://orcid.org/0000-0002-9232-8972","observed_orcids":["https://orcid.org/0000-0002-9232-8972"]},"institutions":[{"id":"https://openalex.org/I4210147543","display_name":"Universidade Estadual do Amap\u00e1","ror":"https://ror.org/04m21mw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210147543"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Hida, Clayton Suguio","raw_affiliation_strings":["UEAP Macap\u00e1 -AP -Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UEAP Macap\u00e1 -AP -Brazil","institution_ids":["https://openalex.org/I4210147543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4868,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82409639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.5971999764442444,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.5971999764442444,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.3621000051498413,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.004399999976158142,"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/large-language-models","display_name":"large language models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/systematic-review-screening","display_name":"systematic review screening","score":0.7200000286102295},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9679999947547913},{"id":"https://openalex.org/keywords/batch-processing","display_name":"batch processing","score":0.9390000104904175},{"id":"https://openalex.org/keywords/imbalanced-binary-classification","display_name":"imbalanced binary classification","score":0.8529999852180481},{"id":"https://openalex.org/keywords/behavioral-decision-making","display_name":"behavioral decision making","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.59579998254776},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.46700000762939453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4478999972343445},{"id":"https://openalex.org/C100253034","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Systematic error","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.41359999775886536},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14737","pdf_url":"https://arxiv.org/pdf/2608.14737","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.2608.14737","doi":"https://doi.org/10.48550/arxiv.2608.14737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14737","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:2608.14737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14737","pdf_url":"https://arxiv.org/pdf/2608.14737","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203709730.pdf","grobid_xml":"https://content.openalex.org/works/W7203709730.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4388747879","https://openalex.org/W4416534882","https://openalex.org/W7149565489","https://openalex.org/W7159580098","https://openalex.org/W7202387926"],"related_works":["https://openalex.org/W7159580098","https://openalex.org/W7214576452","https://openalex.org/W4413974587","https://openalex.org/W7221504577","https://openalex.org/W7172297837","https://openalex.org/W7203720463","https://openalex.org/W7153479913","https://openalex.org/W7172325417","https://openalex.org/W7161704646","https://openalex.org/W4415949686"],"abstract_inverted_index":{"This":[0],"study":[1,9],"analyses":[2,73],"LLMs":[3],"in":[4,11,22,86,92],"imbalanced":[5],"binary":[6],"classification,":[7],"using":[8],"screening":[10],"systematic":[12],"reviews":[13],"as":[14],"the":[15,42,64,67],"application":[16],"domain.":[17],"An":[18],"experiment":[19],"was":[20],"conducted":[21],"five":[23],"reviews,":[24],"comparing":[25],"individual":[26],"and":[27,31,71],"batch":[28,54,79],"processing,":[29],"with":[30,45],"without":[32],"prevalence":[33,43,65],"metadata.":[34],"The":[35,69],"results":[36],"indicate":[37],"a":[38],"limited":[39],"influence":[40],"of":[41,66,88],"metadata,":[44],"no":[46],"evidence":[47],"that":[48,60],"it":[49],"improves":[50],"performance.":[51],"In":[52],"contrast,":[53],"processing":[55,80],"produced":[56],"larger":[57],"behavioral":[58],"changes":[59],"varied":[61],"according":[62],"to":[63,94],"class.":[68],"aggregate":[70],"item-level":[72],"did":[74],"not":[75,84],"always":[76],"coincide.":[77],"Therefore,":[78],"should":[81],"be":[82],"evaluated":[83],"only":[85],"terms":[87],"cost,":[89],"but":[90],"also":[91],"relation":[93],"its":[95],"effects":[96],"on":[97],"decision-making":[98],"behavior.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}