{"id":"https://openalex.org/W4416036987","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.264","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","display_name":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036987","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.264"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.264","pdf_url":"https://aclanthology.org/2025.emnlp-main.264.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.264.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080103571","display_name":"Zexuan Li","orcid":"https://orcid.org/0009-0004-7067-6572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076554923","display_name":"Hongliang Dai","orcid":"https://orcid.org/0000-0002-6974-7167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongliang Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061435467","display_name":"Piji Li","orcid":"https://orcid.org/0000-0003-1474-3692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piji Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87255379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5220","last_page":"5238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3346000015735626,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3346000015735626,"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/T10028","display_name":"Topic Modeling","score":0.21369999647140503,"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/T13629","display_name":"Text Readability and Simplification","score":0.1703999936580658,"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/relation","display_name":"Relation (database)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5351999998092651},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4309999942779541},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3190000057220459},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.30000001192092896}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6722000241279602},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503000259399414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.630299985408783},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5351999998092651},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.264","pdf_url":"https://aclanthology.org/2025.emnlp-main.264.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.264","pdf_url":"https://aclanthology.org/2025.emnlp-main.264.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2394944468","display_name":null,"funder_award_id":"NJ2023032","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322438","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324804","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320330725","display_name":"Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036987.pdf","grobid_xml":"https://content.openalex.org/works/W4416036987.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"For":[0],"Relation":[1,161,163],"Extraction":[2],"(RE),":[3],"the":[4,15,19,97,152,157],"manual":[5],"annotation":[6],"of":[7,99,154,156],"training":[8,44,50,140,176],"data":[9],"may":[10],"be":[11,25],"prohibitively":[12],"expensive,":[13],"since":[14],"sentences":[16],"that":[17,40],"contain":[18],"target":[20],"relations":[21],"in":[22,60,86,124,173],"texts":[23,48,144,180],"can":[24,41,114],"very":[26],"scarce":[27],"and":[28,165],"difficult":[29],"to":[30,35,94,103,138,150],"find.It":[31],"is":[32],"therefore":[33],"beneficial":[34],"develop":[36],"an":[37],"efficient":[38],"method":[39],"automatically":[42],"extract":[43,139],"instances":[45,141],"from":[46,70,142,178],"unlabeled":[47,143,179],"for":[49,76,110,128,145,181],"RE":[51,67,77],"models.Recently,":[52],"large":[53],"language":[54,63],"models":[55],"(LLMs)":[56],"have":[57],"been":[58],"adopted":[59],"various":[61],"natural":[62],"processing":[64],"tasks,":[65],"with":[66,78],"also":[68],"benefiting":[69],"their":[71],"advances.However,":[72],"when":[73],"leveraging":[74],"LLMs":[75,91],"predefined":[79],"relation":[80,112],"categories,":[81],"two":[82],"key":[83],"challenges":[84],"arise.First,":[85],"a":[87,134],"multi-class":[88],"classification":[89,109,159],"setting,":[90],"often":[92],"struggle":[93],"comprehensively":[95],"capture":[96],"semantics":[98],"every":[100],"relation,":[101],"leading":[102],"suboptimal":[104],"results.Second,":[105],"although":[106],"employing":[107],"binary":[108],"each":[111],"individually":[113],"mitigate":[115],"this":[116,131],"issue,":[117],"it":[118],"introduces":[119],"significant":[120],"computational":[121],"overhead,":[122],"resulting":[123],"impractical":[125],"time":[126],"complexity":[127],"real-world":[129],"applications.Therefore,":[130],"paper":[132],"proposes":[133],"framework":[135],"called":[136],"M-BRe":[137],"RE.It":[146],"utilizes":[147],"three":[148],"modules":[149],"combine":[151],"advantages":[153],"both":[155],"above":[158],"approaches:":[160],"Grouping,":[162],"Extraction,":[164],"Label":[166],"Decision.Extensive":[167],"experiments":[168],"confirm":[169],"its":[170],"superior":[171],"capability":[172],"discovering":[174],"high-quality":[175],"samples":[177],"RE.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}