{"id":"https://openalex.org/W7130603642","doi":"https://doi.org/10.1109/fllm67465.2025.11391146","title":"Cal-X: Enhancing Systematic Review Screening with LLMs and Next-Token Likelihood Calibration","display_name":"Cal-X: Enhancing Systematic Review Screening with LLMs and Next-Token Likelihood Calibration","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130603642","doi":"https://doi.org/10.1109/fllm67465.2025.11391146"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11391146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"review","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/A5095928418","display_name":"Elias Sandner","orcid":null},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Elias Sandner","raw_affiliation_strings":["CERN,IT Department,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN,IT Department,Geneva,Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126441262","display_name":"Mario Negoveti\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mario Negoveti\u0107","raw_affiliation_strings":["Technical University Graz,Cognitive & Digital Science Lab,Graz,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Graz,Cognitive & Digital Science Lab,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027850063","display_name":"Kavita Kothari","orcid":"https://orcid.org/0000-0002-0759-5225"},"institutions":[{"id":"https://openalex.org/I4210103171","display_name":"Library Network","ror":"https://ror.org/00qs4g887","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210103171"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kavita Kothari","raw_affiliation_strings":["WHO,Consultant to Library & Digital Information Networks,Kobe,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WHO,Consultant to Library & Digital Information Networks,Kobe,Japan","institution_ids":["https://openalex.org/I4210103171"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126396498","display_name":"Imran Taj","orcid":null},"institutions":[{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Imran Taj","raw_affiliation_strings":["Zayed University,College of Interdisciplinary Studies,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University,College of Interdisciplinary Studies,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I91044093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103079603","display_name":"Luca Fontana","orcid":"https://orcid.org/0000-0002-8614-4114"},"institutions":[{"id":"https://openalex.org/I4210105654","display_name":"World Health Organization","ror":"https://ror.org/01f80g185","country_code":"CH","type":"government","lineage":["https://openalex.org/I4210105654"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Fontana","raw_affiliation_strings":["WHO,Health Emergencies Programme,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WHO,Health Emergencies Programme,Geneva,Switzerland","institution_ids":["https://openalex.org/I4210105654"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039561224","display_name":"Andre Henriques","orcid":"https://orcid.org/0000-0003-1521-3423"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andre Henriques","raw_affiliation_strings":["CERN,Occupational Health & Safety and Environmental Protection (HSE) Unit,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN,Occupational Health & Safety and Environmental Protection (HSE) Unit,Geneva,Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085352389","display_name":"Igor Jakovljevic","orcid":"https://orcid.org/0000-0003-1893-9553"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Igor Jakovljevi\u0107","raw_affiliation_strings":["CERN,IT Department,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN,IT Department,Geneva,Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126382395","display_name":"Alice Simniceanu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105654","display_name":"World Health Organization","ror":"https://ror.org/01f80g185","country_code":"CH","type":"government","lineage":["https://openalex.org/I4210105654"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alice Simniceanu","raw_affiliation_strings":["WHO,Health Emergencies Programme,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WHO,Health Emergencies Programme,Geneva,Switzerland","institution_ids":["https://openalex.org/I4210105654"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838184","display_name":"Andreas Wagner","orcid":"https://orcid.org/0000-0001-9589-2635"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Wagner","raw_affiliation_strings":["CERN,IT Department,Geneva,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN,IT Department,Geneva,Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005301914","display_name":"Christian G\u00fctl","orcid":"https://orcid.org/0000-0001-9589-1966"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christian G\u00fctl","raw_affiliation_strings":["Technical University Graz,Cognitive & Digital Science Lab,Graz,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Graz,Cognitive & Digital Science Lab,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73318633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1071","last_page":"1078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10206","display_name":"Meta-analysis and systematic reviews","score":0.7874000072479248,"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"}},"topics":[{"id":"https://openalex.org/T10206","display_name":"Meta-analysis and systematic reviews","score":0.7874000072479248,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.027300000190734863,"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/T12488","display_name":"Mental Health via Writing","score":0.018799999728798866,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7652999758720398},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6934999823570251},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6574000120162964},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.592199981212616},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5220000147819519},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.510699987411499},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.4749000072479248}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7652999758720398},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6934999823570251},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060000061988831},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.592199981212616},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4968999922275543},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.4749000072479248},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C100253034","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Systematic error","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11391146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313559","display_name":"CERN","ror":"https://ror.org/01ggx4157"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2512040454","https://openalex.org/W2774587119","https://openalex.org/W3002050776","https://openalex.org/W3095902429","https://openalex.org/W3110318438","https://openalex.org/W3169933308","https://openalex.org/W4387144848","https://openalex.org/W4392964628","https://openalex.org/W4406892577","https://openalex.org/W7128199163"],"related_works":[],"abstract_inverted_index":{"Automating":[0],"the":[1,16,45,82,103,149,168,181],"literature":[2],"screening":[3,51,59],"stage":[4],"of":[5,69,105,141],"systematic":[6,83,121],"reviews":[7,122,128],"can":[8],"substantially":[9],"reduce":[10],"time":[11],"and":[12,123,144,192,206],"costs":[13],"while":[14,109,157],"maintaining":[15],"quality":[17],"standards":[18],"required":[19,47],"for":[20,32,65,98,233],"reliable":[21],"evidence":[22],"synthesis.":[23],"Although":[24],"Large":[25],"Language":[26],"Models":[27],"(LLMs)":[28],"have":[29],"shown":[30],"promise":[31],"this":[33,217],"task,":[34],"most":[35],"existing":[36],"approaches":[37],"fail":[38],"to":[39,48,77,159,167],"consistently":[40],"achieve":[41],"sensitivity":[42,139,161,198,224],"above":[43],"99%,":[44],"threshold":[46],"replace":[49],"human":[50,99],"in":[52,203,216],"high-quality":[53],"reviews.This":[54],"study":[55,218],"introduces":[56],"CAL-X,":[57],"a":[58,87,163,195],"algorithm":[60,150,171],"that":[61,93,220],"employs":[62],"an":[63],"LLM":[64],"initial":[66],"binary":[67],"classification":[68],"candidate":[70],"studies,":[71],"followed":[72],"by":[73,153],"next-token-likelihood":[74],"(NTL)\u2013based":[75],"reclassification":[76],"optimize":[78],"sensitivity.":[79],"Integrated":[80],"into":[81],"review":[84],"workflow":[85],"as":[86,197],"pre-filtration":[88],"system,":[89],"it":[90],"retains":[91],"studies":[92,108],"cannot":[94],"be":[95],"confidently":[96],"excluded":[97],"screening,":[100],"thereby":[101],"minimizing":[102],"risk":[104],"missing":[106],"relevant":[107],"still":[110],"significantly":[111],"reducing":[112],"workload.CAL-X":[113],"was":[114],"calibrated":[115],"using":[116],"data":[117],"from":[118,129],"13":[119],"published":[120],"evaluated":[124],"on":[125,155,180],"17":[126],"additional":[127],"diverse":[130],"domains.":[131],"Across":[132],"all":[133],"evaluation":[134],"datasets,":[135],"CAL-X":[136,174],"achieved":[137,184],"average":[138],"targets":[140,199],"95%,":[142],"98%,":[143],"99%.":[145],"At":[146],"99%":[147],"sensitivity,":[148,186],"reduced":[151],"workload":[152,188,207],"20.84%":[154],"average,":[156],"calibration":[158,221],"95%":[160],"yielded":[162],"43.70%":[164],"reduction.":[165],"Compared":[166],"5-tier":[169],"baseline":[170],"proposed":[172],"previously,":[173],"demonstrated":[175],"greater":[176,187],"adaptability":[177],"and,":[178],"depending":[179],"chosen":[182],"threshold,":[183],"higher":[185],"reduction,":[189],"or":[190],"both.Generalizability":[191],"reliability":[193],"remain":[194],"challenge,":[196],"were":[200],"not":[201,230],"met":[202],"some":[204],"cases":[205],"reduction":[208],"varied":[209],"with":[210],"dataset":[211],"characteristics.":[212],"The":[213],"findings":[214],"presented":[215],"show":[219],"toward":[222],"high":[223],"through":[225],"NTL":[226],"is":[227],"feasible":[228],"but":[229],"yet":[231],"ready":[232],"real-world":[234],"application.":[235]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}