{"id":"https://openalex.org/W4392575310","doi":"https://doi.org/10.48550/arxiv.2403.03304","title":"Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types","display_name":"Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392575310","doi":"https://doi.org/10.48550/arxiv.2403.03304"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.03304","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03304","pdf_url":"https://arxiv.org/pdf/2403.03304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086918380","display_name":"Joseph Gatto","orcid":"https://orcid.org/0000-0001-7013-2445","observed_orcids":["https://orcid.org/0000-0001-7013-2445"]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gatto, Joseph","raw_affiliation_strings":["Department of Computer Science , Dartmouth College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Dartmouth College","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035716941","display_name":"Parker Seegmiller","orcid":"https://orcid.org/0000-0001-6783-9773","observed_orcids":["https://orcid.org/0000-0001-6783-9773"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seegmiller, Parker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021361292","display_name":"Omar Sharif","orcid":"https://orcid.org/0000-0002-1971-6522","observed_orcids":["https://orcid.org/0000-0002-1971-6522"]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharif, Omar","raw_affiliation_strings":["Department of Computer Science , Dartmouth College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Dartmouth College","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066969862","display_name":"Sarah Masud Preum","orcid":"https://orcid.org/0000-0002-7771-8323","observed_orcids":["https://orcid.org/0000-0002-7771-8323"]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preum, Sarah M.","raw_affiliation_strings":["Department of Computer Science , Dartmouth College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Dartmouth College","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9833999872207642,"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":0.9833999872207642,"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":0.007400000002235174,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/event-argument-extraction","display_name":"event argument extraction","score":0.9750000238418579},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9100000262260437},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9269999861717224},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.5899999737739563},{"id":"https://openalex.org/keywords/statistical-depth","display_name":"statistical depth","score":0.7490000128746033}],"concepts":[{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.7797906994819641},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6598563194274902},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5125769972801208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4834536015987396},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.4389481842517853},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3655204176902771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22020143270492554},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17474406957626343},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.10942056775093079},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.050922930240631104},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.03304","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03304","pdf_url":"https://arxiv.org/pdf/2403.03304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.03304","doi":"https://doi.org/10.48550/arxiv.2403.03304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03304","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03304","pdf_url":"https://arxiv.org/pdf/2403.03304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392575310.pdf","grobid_xml":"https://content.openalex.org/works/W4392575310.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412889958","https://openalex.org/W4403942899","https://openalex.org/W7140081224","https://openalex.org/W4402670546","https://openalex.org/W4296285526","https://openalex.org/W4416534372","https://openalex.org/W4406461528","https://openalex.org/W4404400436","https://openalex.org/W4312564284","https://openalex.org/W4402953187"],"abstract_inverted_index":{"Event":[0],"Argument":[1],"Extraction":[2],"(EAE)":[3],"is":[4,26],"an":[5],"extremely":[6],"difficult":[7],"information":[8],"extraction":[9,105],"problem":[10],"--":[11],"with":[12,65,142],"significant":[13],"limitations":[14],"in":[15,101,134,147],"few-shot":[16,60],"cross-domain":[17,116],"(FSCD)":[18],"settings.":[19],"A":[20],"common":[21],"solution":[22],"to":[23,36,47,56,67,131,144,163,168],"FSCD":[24],"modeling":[25],"data":[27,79],"augmentation.":[28],"Unfortunately,":[29],"existing":[30],"augmentation":[31,80,156],"methods":[32,96],"are":[33,139],"not":[34],"well-suited":[35],"a":[37,98,121],"variety":[38],"of":[39,106,115],"real-world":[40],"EAE":[41,86],"contexts":[42],"including":[43],"(i)":[44],"The":[45,54],"need":[46,55],"model":[48,57],"long":[49],"documents":[50],"(10+":[51],"sentences)":[52],"(ii)":[53],"zero":[58,89,107],"and":[59],"roles":[61,64,133,145],"(i.e.":[62],"event":[63],"little":[66],"no":[68],"training":[69,91],"representation).":[70],"In":[71],"this":[72],"work,":[73],"we":[74,118],"introduce":[75,120],"two":[76],"novel":[77],"LLM-powered":[78],"frameworks":[81],"for":[82],"synthesizing":[83],"extractive":[84],"document-level":[85],"samples":[87],"using":[88],"in-domain":[90],"data.":[92],"Our":[93,151],"highest":[94],"performing":[95],"provide":[97],"16-pt":[99],"increase":[100],"F1":[102,125,165],"score":[103],"on":[104],"shot":[108],"role":[109],"types.":[110],"To":[111],"better":[112],"facilitate":[113],"analysis":[114],"EAE,":[117],"additionally":[119],"new":[122],"metric,":[123],"Role-Depth":[124],"(RDF1),":[126],"which":[127,138],"uses":[128],"statistical":[129],"depth":[130],"identify":[132],"the":[135,148],"target":[136],"domain":[137],"semantic":[140],"outliers":[141],"respect":[143],"observed":[146],"source":[149],"domain.":[150],"experiments":[152],"show":[153],"that":[154],"LLM-based":[155],"can":[157],"boost":[158],"RDF1":[159],"performance":[160],"by":[161],"up":[162],"11":[164],"points":[166],"compared":[167],"baseline":[169],"methods.":[170]},"counts_by_year":[],"updated_date":"2026-10-02T10:15:12.560889","created_date":"2024-03-08T00:00:00"}