{"id":"https://openalex.org/W4401639961","doi":"https://doi.org/10.1007/s44163-024-00159-8","title":"Cost-efficient prompt engineering for unsupervised entity resolution in the product matching domain","display_name":"Cost-efficient prompt engineering for unsupervised entity resolution in the product matching domain","publication_year":2024,"publication_date":"2024-08-16","ids":{"openalex":"https://openalex.org/W4401639961","doi":"https://doi.org/10.1007/s44163-024-00159-8"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-024-00159-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-024-00159-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-024-00159-8.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-024-00159-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093047836","display_name":"Navapat Nananukul","orcid":"https://orcid.org/0009-0001-2740-4457"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Navapat Nananukul","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093047835","display_name":"Khanin Sisaengsuwanchai","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khanin Sisaengsuwanchai","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074197492","display_name":"Mayank Kejriwal","orcid":"https://orcid.org/0000-0001-5988-8305"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Kejriwal","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093047836"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":990,"currency":"EUR","value_usd":1067},"apc_paid":{"value":990,"currency":"EUR","value_usd":1067},"fwci":7.5899,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.97496179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9902999997138977,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9742000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.684825599193573},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6088314056396484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6011114120483398},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5507428050041199},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5175930261611938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3763847053050995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3579174876213074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3398210108280182},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18913307785987854},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12067458033561707}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.684825599193573},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6088314056396484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011114120483398},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5507428050041199},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5175930261611938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3763847053050995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3579174876213074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3398210108280182},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18913307785987854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12067458033561707},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-024-00159-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-024-00159-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-024-00159-8.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c3a2dccc7dad48bd9eb05b8c1160062e","is_oa":true,"landing_page_url":"https://doaj.org/article/c3a2dccc7dad48bd9eb05b8c1160062e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Artificial Intelligence, Vol 4, Iss 1, Pp 1-21 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-024-00159-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-024-00159-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-024-00159-8.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401639961.pdf","grobid_xml":"https://content.openalex.org/works/W4401639961.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1606941371","https://openalex.org/W1646278814","https://openalex.org/W1742677423","https://openalex.org/W1964786778","https://openalex.org/W1981590391","https://openalex.org/W1985558865","https://openalex.org/W1997927541","https://openalex.org/W2041439319","https://openalex.org/W2065398649","https://openalex.org/W2067566391","https://openalex.org/W2154785834","https://openalex.org/W2164456230","https://openalex.org/W2171472464","https://openalex.org/W2414770401","https://openalex.org/W2544062944","https://openalex.org/W2794291661","https://openalex.org/W2798649495","https://openalex.org/W2905135414","https://openalex.org/W2945883855","https://openalex.org/W2946123203","https://openalex.org/W2946504770","https://openalex.org/W2954807325","https://openalex.org/W2966266770","https://openalex.org/W2981255969","https://openalex.org/W2985009327","https://openalex.org/W3014295153","https://openalex.org/W3029269967","https://openalex.org/W3045854241","https://openalex.org/W3092962901","https://openalex.org/W3138971549","https://openalex.org/W3146259567","https://openalex.org/W3217025781","https://openalex.org/W4212774754","https://openalex.org/W4221143046","https://openalex.org/W4221163653","https://openalex.org/W4242744113","https://openalex.org/W4298196171","https://openalex.org/W4306294746","https://openalex.org/W4306317280","https://openalex.org/W4379598302","https://openalex.org/W4383616803","https://openalex.org/W4386867830","https://openalex.org/W4387848774","https://openalex.org/W4388691793","https://openalex.org/W4389500969","https://openalex.org/W4390873481","https://openalex.org/W4392002118","https://openalex.org/W4392367389","https://openalex.org/W4400909484","https://openalex.org/W6680715191"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W1517180214","https://openalex.org/W4301594054","https://openalex.org/W2082780921","https://openalex.org/W2794488505","https://openalex.org/W2025517136","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W3046451053"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"is":[3,80,199],"the":[4,14,66,90,104,118,179,236],"problem":[5],"of":[6,42,62,92,106,120,235,238,254],"semi-automatically":[7],"determining":[8],"when":[9,256],"two":[10,173,183],"entities":[11],"refer":[12],"to":[13,23,54,145,168,192,242],"same":[15],"underlying":[16],"entity,":[17],"with":[18],"applications":[19],"ranging":[20],"from":[21],"healthcare":[22],"e-commerce.":[24],"Traditional":[25],"ER":[26,56,70,161],"solutions":[27],"required":[28],"considerable":[29],"manual":[30],"expertise,":[31],"including":[32,232],"domain-specific":[33,130],"feature":[34],"engineering,":[35],"as":[36,38,258],"well":[37,82],"identification":[39],"and":[40,59,102,124,159,165,187,210,229],"curation":[41],"training":[43],"data.":[44],"Recently":[45],"released":[46],"large":[47],"language":[48],"models":[49],"(LLMs)":[50],"provide":[51,188,224],"an":[52,195],"opportunity":[53],"make":[55],"more":[57,208],"seamless":[58],"domain-independent.":[60],"Because":[61],"LLMs\u2019":[63],"pre-trained":[64],"knowledge,":[65],"matching":[67,132,171,204],"step":[68],"in":[69,178,262],"can":[71,86,95,109],"be":[72,110],"made":[73],"easier":[74],"by":[75,149],"just":[76],"prompting.":[77],"However,":[78],"it":[79],"also":[81],"known":[83],"that":[84,89,103,194,207],"LLMs":[85,108,255],"pose":[87],"risks,":[88],"quality":[91],"their":[93,125],"outputs":[94],"depend":[96],"on":[97,117,172,227],"how":[98],"prompts":[99],"are":[100],"engineered,":[101],"cost":[105,127],"using":[107,133],"significant.":[111],"Unfortunately,":[112],"a":[113,152,233,259],"systematic":[114],"experimental":[115,190],"study":[116,234],"effects":[119],"different":[121,239],"prompting":[122,215,240],"methods":[123,164,216,241],"respective":[126],"for":[128,201],"solving":[129],"entity":[131],"LLMs,":[134],"like":[135,197],"ChatGPT,":[136],"has":[137],"been":[138],"lacking":[139],"thus":[140],"far.":[141],"This":[142],"paper":[143],"aims":[144],"address":[146],"this":[147],"gap":[148],"conducting":[150],"such":[151],"study.":[153],"We":[154,181,223],"consider":[155,251],"some":[156,252],"relatively":[157],"simple":[158],"cost-efficient":[160],"prompt":[162],"engineering":[163],"apply":[166],"them":[167],"perform":[169],"product":[170,203,260],"real-world":[174,264],"datasets":[175,186],"widely":[176],"used":[177,257],"community.":[180],"select":[182],"well-known":[184],"e-commerce":[185,265],"extensive":[189],"results":[191],"show":[193],"LLM":[196],"GPT3.5":[198],"viable":[200],"high-performing":[202],"and,":[205],"interestingly,":[206],"complicated":[209],"detailed":[211],"(and":[212],"hence,":[213],"expensive)":[214],"do":[217],"not":[218],"necessarily":[219],"outperform":[220],"simpler":[221],"approaches.":[222],"brief":[225],"discussions":[226],"qualitative":[228],"error":[230],"analysis,":[231],"inter-consistency":[237],"determine":[243],"whether":[244],"they":[245],"yield":[246],"stable":[247],"outputs.":[248],"Finally,":[249],"we":[250],"limitations":[253],"matcher":[261],"potential":[263],"applications.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}