{"id":"https://openalex.org/W7117896021","doi":"https://doi.org/10.1109/access.2025.3650469","title":"Diversified Prompting Strategy for Improving Slot Filling With Large Language Models","display_name":"Diversified Prompting Strategy for Improving Slot Filling With Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7117896021","doi":"https://doi.org/10.1109/access.2025.3650469"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3650469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3650469","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3650469","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121745589","display_name":"Mirr Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Mirr Shin","raw_affiliation_strings":["Department of Computer Science and Engineering, Incheon National University, Yeonsu-gu, Incheon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Incheon National University, Yeonsu-gu, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007388983","display_name":"Youhyun Shin","orcid":"https://orcid.org/0000-0001-7013-9057"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youhyun Shin","raw_affiliation_strings":["Department of Computer Science and Engineering, Incheon National University, Yeonsu-gu, Incheon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Incheon National University, Yeonsu-gu, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121745589"],"corresponding_institution_ids":["https://openalex.org/I146429904"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02032029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"4605","last_page":"4626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7878000140190125,"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":0.7878000140190125,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06870000064373016,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.017799999564886093,"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/benchmark","display_name":"Benchmark (surveying)","score":0.745199978351593},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6772000193595886},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6764000058174133},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6693999767303467},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5224000215530396},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4880000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026999831199646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.745199978351593},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6772000193595886},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6764000058174133},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6693999767303467},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3650469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3650469","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3650469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3650469","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8789236310","display_name":null,"funder_award_id":"2023","funder_id":"https://openalex.org/F4320321363","funder_display_name":"Incheon National University"}],"funders":[{"id":"https://openalex.org/F4320321363","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2964006684","https://openalex.org/W2965373594","https://openalex.org/W3153427360","https://openalex.org/W3167277949","https://openalex.org/W3172697791","https://openalex.org/W3175327592","https://openalex.org/W3176489198","https://openalex.org/W3176733230","https://openalex.org/W3196967363","https://openalex.org/W3199079601","https://openalex.org/W4224903953","https://openalex.org/W4287887868","https://openalex.org/W4382202738","https://openalex.org/W4385570584","https://openalex.org/W4385571765","https://openalex.org/W4385572438","https://openalex.org/W4386566800","https://openalex.org/W4389518803"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,158],"diversified":[3,146],"prompting":[4,147],"strategy":[5,36,148],"to":[6,29,46,58,116,122,132],"address":[7],"the":[8,59,101,134,144],"challenges":[9],"of":[10,137],"slot":[11,33,63,164],"filling":[12],"with":[13,85,100],"Large":[14],"Language":[15],"Models":[16],"(LLMs),":[17],"where":[18],"recall":[19,73,113],"often":[20],"suffers":[21],"from":[22,114,120],"prediction":[23],"omissions":[24],"and":[25,49,74,83,93,103,118,155],"precision":[26],"declines":[27],"due":[28],"duplicate":[30],"or":[31],"excessive":[32],"assignments.":[34],"Our":[35],"combines":[37],"sub-prompt,":[38],"which":[39,52],"partitions":[40],"candidate":[41],"slots":[42],"into":[43],"smaller":[44],"groups":[45],"improve":[47],"recall,":[48,153],"multi-view":[50],"prompt,":[51],"applies":[53],"diverse":[54],"structural":[55],"prompt":[56],"variations":[57],"same":[60],"utterance.":[61],"Final":[62],"predictions":[64],"are":[65],"selected":[66],"through":[67],"threshold-based":[68],"majority":[69],"voting,":[70],"effectively":[71,149],"balancing":[72],"precision.":[75],"Experiments":[76],"on":[77,109],"three":[78],"benchmark":[79],"datasets":[80],"(SNIPS,":[81],"MASSIVE,":[82],"MultiWoz)":[84],"six":[86],"LLMs":[87],"(bloomz,":[88],"falcon,":[89],"llama2,":[90],"llama3,":[91],"qwen2,":[92],"gemma)":[94],"show":[95],"consistent":[96],"improvements":[97],"when":[98],"compared":[99],"baseline":[102],"all":[104],"single-prompt":[105],"methods.":[106],"For":[107],"example,":[108],"SNIPS,":[110],"llama3-8B":[111],"improves":[112],"78.4":[115],"90.5":[117],"F1":[119],"72.6":[121],"82.0.":[123],"Additionally,":[124],"we":[125],"conducted":[126],"experiments":[127],"across":[128],"various":[129],"model":[130],"sizes":[131],"confirm":[133],"general":[135],"applicability":[136],"our":[138],"methodology.":[139],"These":[140],"results":[141],"demonstrate":[142],"that":[143],"proposed":[145],"restores":[150],"balance":[151],"among":[152],"precision,":[154],"F1,":[156],"offering":[157],"scalable":[159],"methodology":[160],"for":[161],"enhancing":[162],"LLM-based":[163],"filling.":[165]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-01T00:00:00"}