{"id":"https://openalex.org/W7127079522","doi":"https://doi.org/10.1016/j.knosys.2026.115427","title":"The impact of fine-tuning on entity resolution: An experimental evaluation","display_name":"The impact of fine-tuning on entity resolution: An experimental evaluation","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127079522","doi":"https://doi.org/10.1016/j.knosys.2026.115427"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.115427","doi":"https://doi.org/10.1016/j.knosys.2026.115427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115427","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2026.115427","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021354735","display_name":"Dimitrios Karapiperis","orcid":"https://orcid.org/0000-0002-3878-5988","observed_orcids":["https://orcid.org/0000-0002-3878-5988"]},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Dimitrios Karapiperis","raw_affiliation_strings":["organization=International Hellenic University, country=Greece"],"raw_orcid":"https://orcid.org/0000-0002-3878-5988","affiliations":[{"raw_affiliation_string":"organization=International Hellenic University, country=Greece","institution_ids":["https://openalex.org/I183898223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011200753","display_name":"Leonidas Akritidis","orcid":"https://orcid.org/0000-0001-6602-0723","observed_orcids":["https://orcid.org/0000-0001-6602-0723"]},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Leonidas Akritidis","raw_affiliation_strings":["organization=International Hellenic University, country=Greece"],"raw_orcid":"https://orcid.org/0000-0001-6602-0723","affiliations":[{"raw_affiliation_string":"organization=International Hellenic University, country=Greece","institution_ids":["https://openalex.org/I183898223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011619520","display_name":"Panayiotis Bozanis","orcid":"https://orcid.org/0000-0001-9435-1829","observed_orcids":["https://orcid.org/0000-0001-9435-1829"]},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Panayiotis Bozanis","raw_affiliation_strings":["organization=International Hellenic University, country=Greece"],"raw_orcid":"https://orcid.org/0000-0001-9435-1829","affiliations":[{"raw_affiliation_string":"organization=International Hellenic University, country=Greece","institution_ids":["https://openalex.org/I183898223"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011200753","https://openalex.org/A5011619520","https://openalex.org/A5021354735"],"corresponding_institution_ids":["https://openalex.org/I183898223"],"apc_list":{"value":3430,"currency":"USD","value_usd":3430},"apc_paid":{"value":3430,"currency":"USD","value_usd":3430},"fwci":6.4867,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92629313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"338","issue":null,"first_page":"115427","last_page":"115427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10028","display_name":"Topic Modeling","score":0.03319999948143959,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":9.999999747378752e-05,"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/entity-resolution","display_name":"entity resolution","score":0.9990000128746033},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.925000011920929},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.906000018119812},{"id":"https://openalex.org/keywords/bi-encoder","display_name":"bi-encoder","score":0.9570000171661377},{"id":"https://openalex.org/keywords/cross-encoder","display_name":"cross-encoder","score":1.0},{"id":"https://openalex.org/keywords/minilm","display_name":"MiniLM","score":0.9580000042915344},{"id":"https://openalex.org/keywords/mpnet","display_name":"MPNet","score":0.9919999837875366},{"id":"https://openalex.org/keywords/accuracy-efficiency-trade-off","display_name":"accuracy-efficiency trade-off","score":0.9419999718666077},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.48899999260902405},{"id":"https://openalex.org/keywords/training-costs","display_name":"training costs","score":0.6570000052452087},{"id":"https://openalex.org/keywords/resolution-time","display_name":"time to resolution","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8216000199317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286999821662903},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2779977028","wikidata":"https://www.wikidata.org/wiki/Q1493813","display_name":"Gap analysis (conservation)","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.115427","doi":"https://doi.org/10.1016/j.knosys.2026.115427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115427","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2026.115427","doi":"https://doi.org/10.1016/j.knosys.2026.115427","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115427","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2963469388","https://openalex.org/W3032015135","https://openalex.org/W3104748221","https://openalex.org/W3155747247","https://openalex.org/W3217025781","https://openalex.org/W4397029689","https://openalex.org/W4405047605","https://openalex.org/W4415124086"],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"pre-trained":[1,90,102,191],"language":[2],"models":[3,54,91,192],"has":[4,15],"become":[5],"the":[6,61,139,143,169,206],"state-of-the-art":[7],"approach":[8],"for":[9,60,202],"Entity":[10],"Resolution":[11],"(ER),":[12],"but":[13,183],"this":[14,78],"created":[16],"a":[17,29,101,104,108,134,160,199],"divide":[18],"between":[19,146],"two":[20],"dominant":[21],"architectures:":[22],"fast-but-less-accurate":[23],"bi-encoders":[24],"and":[25,55,72,94,107,119,127,148,209,216],"accurate-but-slow":[26],"cross-encoders.":[27],"However,":[28],"concrete":[30],"gap":[31,79],"in":[32,43],"prior":[33],"ER":[34,66],"benchmarking":[35],"remains":[36,50],"unresolved:":[37],"existing":[38],"studies":[39],"often":[40],"evaluate":[41],"architectures":[42,56],"isolation":[44],"or":[45],"on":[46,115,168,175,188,204,212],"limited":[47],"datasets.":[48],"It":[49],"unclear":[51],"which":[52],"base":[53],"are":[57,193],"best":[58],"suited":[59],"diverse":[62,117],"range":[63],"of":[64],"real-world":[65,118],"datasets,":[67,121],"each":[68],"with":[69],"unique":[70],"characteristics":[71],"performance":[73,147,181,187],"bottlenecks.":[74],"This":[75],"paper":[76],"bridges":[77],"through":[80],"an":[81],"extensive":[82],"empirical":[83],"evaluation.":[84],"We":[85,111],"systematically":[86],"compare":[87],"three":[88,97],"popular":[89],"(MiniLM,":[92],"MPNet,":[93],"BGE)":[95],"across":[96],"distinct":[98],"architectural":[99],"paradigms:":[100],"bi-encoder,":[103,106],"fine-tuned":[105,109,140],"cross-encoder.":[110],"tested":[112],"these":[113],"combinations":[114],"eight":[116],"semi-synthetic":[120],"analyzing":[122],"their":[123,213],"performance,":[124],"training":[125],"costs,":[126],"final":[128],"resolution":[129,150],"times.":[130],"Our":[131],"results":[132],"reveal":[133],"clear":[135],"accuracy-vs-efficiency":[136],"trade-off,":[137],"identifying":[138],"bi-encoder":[141],"as":[142],"optimal":[144,207],"balance":[145],"practical":[149,200],"speed.":[151],"More":[152],"importantly,":[153],"we":[154],"demonstrate":[155],"that":[156],"fine-tuning":[157],"is":[158,165,184],"not":[159],"universal":[161],"solution.":[162],"Its":[163],"effectiveness":[164],"highly":[166],"contingent":[167],"dataset:":[170],"it":[171],"provides":[172],"substantial":[173],"gains":[174],"specialized":[176],"domains":[177],"by":[178],"fixing":[179],"pre-existing":[180],"gaps":[182],"detrimental":[185],"to":[186],"datasets":[189],"where":[190],"already":[194],"well-aligned.":[195],"These":[196],"findings":[197],"provide":[198],"guide":[201],"practitioners":[203],"selecting":[205],"model":[208],"architecture":[210],"based":[211],"specific":[214],"data":[215],"application":[217],"requirements.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2026-02-03T00:00:00"}