{"id":"https://openalex.org/W4416251810","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228382","title":"LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs","display_name":"LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251810","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228382"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5117865131","display_name":"Umesh Bodhwani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umesh Bodhwani","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102872221","display_name":"Yuan Ling","orcid":"https://orcid.org/0000-0002-1135-5240"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Ling","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063365610","display_name":"C. Senthilkumar","orcid":"https://orcid.org/0000-0002-0268-3701"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cibi Chakravarthy Senthilkumar","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029177452","display_name":"Shujing Dong","orcid":"https://orcid.org/0009-0008-0240-681X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shujing Dong","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008758382","display_name":"Yarong Feng","orcid":"https://orcid.org/0000-0001-7595-6945"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yarong Feng","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339418","display_name":"Hong Li","orcid":"https://orcid.org/0000-0002-8659-086X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfei Li","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038027729","display_name":"Ayush Goyal","orcid":"https://orcid.org/0000-0002-1585-8806"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayush Goyal","raw_affiliation_strings":["Amazon,Seattle,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17600032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3799999952316284,"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":0.3799999952316284,"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/T11719","display_name":"Data Quality and Management","score":0.3174999952316284,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.11969999969005585,"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/cluster-analysis","display_name":"Cluster analysis","score":0.5514000058174133},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.48989999294281006},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41339999437332153},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4131999909877777},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37529999017715454},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.365200012922287},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3495999872684479},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.31940001249313354},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.3163999915122986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474999785423279},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1981208470","https://openalex.org/W2898810549","https://openalex.org/W4385572634","https://openalex.org/W4386576685","https://openalex.org/W4389518632","https://openalex.org/W4389519192","https://openalex.org/W4389520497","https://openalex.org/W4393161145","https://openalex.org/W4400531953"],"related_works":[],"abstract_inverted_index":{"Latent":[0,53],"entity":[1,19,35,165],"extraction":[2,20,36,168],"(LEE)":[3],"tackles":[4],"the":[5,79,109,116,133],"challenge":[6],"of":[7,81,118],"identifying":[8],"implicit,":[9],"contextually":[10,92],"inferred":[11],"entities":[12],"within":[13],"free":[14],"text\u2014an":[15],"area":[16],"where":[17],"traditional":[18],"methods":[21],"fall":[22],"short.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"introduce":[28],"LentEx,":[29],"a":[30,86,160],"novel":[31],"framework":[32],"for":[33,63,163],"latent":[34,164],"that":[37],"leverages":[38],"synthetic":[39,94],"data":[40],"generation":[41,68],"and":[42,59,73,99,156,167],"instruction":[43],"fine-tuning":[44],"to":[45,89,111,143],"optimize":[46],"smaller,":[47],"efficient":[48],"large":[49],"language":[50,171],"models":[51,131],"(LLMs).":[52],"entities,":[54],"which":[55],"are":[56,61],"often":[57],"abstract":[58],"thematic,":[60],"crucial":[62],"applications":[64],"such":[65],"as":[66],"retrieval-augmented":[67],"(RAG),":[69],"customer":[70],"persona":[71],"analysis,":[72],"knowledge":[74],"graph":[75],"enrichment.":[76],"LentEx":[77,107,120,147],"addresses":[78],"scarcity":[80],"labeled":[82],"datasets":[83],"by":[84],"employing":[85],"template-based":[87],"approach":[88,113],"generate":[90],"diverse,":[91],"rich":[93],"data,":[95],"ensuring":[96],"high":[97],"variability":[98],"alignment":[100],"with":[101],"real-world":[102,151],"distributions.":[103],"To":[104],"our":[105,138],"knowledge,":[106],"is":[108],"first":[110],"systematically":[112],"LEE":[114],"through":[115],"lens":[117],"LLMs.":[119],"demonstrates":[121],"significant":[122],"performance":[123],"improvements":[124],"across":[125],"multiple":[126],"tasks,":[127,153],"notably":[128],"surpassing":[129],"state-of-the-art":[130],"on":[132],"MTEB":[134],"Clustering":[135],"Benchmark.":[136],"Furthermore,":[137],"methodology":[139],"enables":[140],"robust":[141],"generalization":[142],"unseen":[144],"domains,":[145],"making":[146],"highly":[148],"applicable":[149],"in":[150,169],"NLP":[152],"including":[154],"RAG":[155],"clustering,":[157],"thereby":[158],"establishing":[159],"new":[161],"paradigm":[162],"understanding":[166],"natural":[170],"processing.":[172]},"counts_by_year":[],"updated_date":"2025-11-28T09:27:05.834982","created_date":"2025-11-14T00:00:00"}