{"id":"https://openalex.org/W4412886951","doi":"https://doi.org/10.18653/v1/2025.acl-long.35","title":"Generating Diverse Training Samples for Relation Extraction with Large Language Models","display_name":"Generating Diverse Training Samples for Relation Extraction with Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886951","doi":"https://doi.org/10.18653/v1/2025.acl-long.35"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.35","pdf_url":"https://aclanthology.org/2025.acl-long.35.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.35.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":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"713","last_page":"726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9900000095367432,"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":0.9900000095367432,"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":0.9891999959945679,"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/relationship-extraction","display_name":"Relationship extraction","score":0.7454392910003662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6994912028312683},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6560312509536743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5691947340965271},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5426547527313232},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.48208218812942505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4503898322582245},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41133302450180054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2042878270149231},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06263253092765808}],"concepts":[{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.7454392910003662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6994912028312683},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6560312509536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5691947340965271},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5426547527313232},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.48208218812942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4503898322582245},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41133302450180054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2042878270149231},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06263253092765808},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.35","pdf_url":"https://aclanthology.org/2025.acl-long.35.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.35","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.35","pdf_url":"https://aclanthology.org/2025.acl-long.35.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"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/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"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/W4412886951.pdf","grobid_xml":"https://content.openalex.org/works/W4412886951.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W4392969631","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W4221160509","https://openalex.org/W2547211086","https://openalex.org/W2538200646","https://openalex.org/W1968988659","https://openalex.org/W2888033806"],"abstract_inverted_index":{"Using":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"to":[5,15,25,56,78,99,119,173],"generate":[6],"training":[7,85,124,149,162],"data":[8],"can":[9,142],"potentially":[10],"be":[11,26],"a":[12,58,68,163],"preferable":[13],"way":[14],"improve":[16,80,143],"zero":[17],"or":[18],"few-shot":[19],"NLP":[20],"tasks.However,":[21],"many":[22],"problems":[23],"remain":[24],"investigated":[27],"for":[28,90,122],"this":[29,73],"direction.For":[30],"the":[31,65,81,84,101,144,147],"task":[32],"of":[33,61,70,83,146],"Relation":[34],"Extraction":[35],"(RE),":[36],"we":[37,75,115],"find":[38,152],"that":[39,139,153],"samples":[40,86,105,170],"generated":[41,87,148,169],"by":[42,106],"directly":[43,107,156],"prompting":[44],"LLMs":[45,89,102,121],"may":[46,171],"easily":[47],"have":[48],"high":[49],"structural":[50],"similarities":[51],"with":[52,88,155,159,167],"each":[53],"other.They":[54],"tend":[55],"use":[57],"limited":[59],"variety":[60],"phrasing":[62],"while":[63,92],"expressing":[64],"relation":[66],"between":[67],"pair":[69],"entities.Therefore,":[71],"in":[72,110],"paper,":[74],"study":[76],"how":[77],"effectively":[79],"diversity":[82,123],"RE,":[91],"also":[93,151],"maintaining":[94],"their":[95],"correctness.We":[96],"first":[97],"try":[98],"make":[100],"produce":[103],"dissimilar":[104],"giving":[108],"instructions":[109],"In-Context":[111],"Learning":[112],"(ICL)":[113],"prompts.Then,":[114],"propose":[116],"an":[117,160],"approach":[118],"fine-tune":[120],"sample":[125],"generation":[126],"through":[127],"Direct":[128],"Preference":[129],"Optimization":[130],"(DPO).Our":[131],"experiments":[132],"on":[133],"commonly":[134],"used":[135],"RE":[136,158,165],"datasets":[137],"show":[138],"both":[140],"attempts":[141],"quality":[145],"data.We":[150],"comparing":[154],"performing":[157],"LLM,":[161],"non-LLM":[164],"model":[166],"its":[168],"lead":[172],"better":[174],"performance.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}