{"id":"https://openalex.org/W4416034606","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.649","title":"REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction","display_name":"REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034606","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.649"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.649","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.649","pdf_url":"https://aclanthology.org/2025.findings-emnlp.649.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.649.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021361292","display_name":"Omar Sharif","orcid":"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"]},{"id":"https://openalex.org/I4210166639","display_name":"Dartmouth Hospital","ror":"https://ror.org/02j3qj605","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210166639"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Omar Sharif","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/I4210166639","https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086918380","display_name":"Joseph Gatto","orcid":"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"]},{"id":"https://openalex.org/I4210166639","display_name":"Dartmouth Hospital","ror":"https://ror.org/02j3qj605","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210166639"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Joseph Gatto","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/I4210166639","https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112935114","display_name":"Madhusudan Basak","orcid":null},"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"]},{"id":"https://openalex.org/I4210166639","display_name":"Dartmouth Hospital","ror":"https://ror.org/02j3qj605","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210166639"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Madhusudan Basak","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/I4210166639","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"},"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"]},{"id":"https://openalex.org/I4210166639","display_name":"Dartmouth Hospital","ror":"https://ror.org/02j3qj605","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210166639"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sarah Masud Preum","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/I4210166639","https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15731974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12146","last_page":"12168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.582099974155426,"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":0.582099974155426,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.050700001418590546,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6195999979972839},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.423799991607666},{"id":"https://openalex.org/keywords/event-data","display_name":"Event data","score":0.3481000065803528},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.30469998717308044},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.26499998569488525}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.649","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.649","pdf_url":"https://aclanthology.org/2025.findings-emnlp.649.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.649","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.649","pdf_url":"https://aclanthology.org/2025.findings-emnlp.649.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034606.pdf","grobid_xml":"https://content.openalex.org/works/W4416034606.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Event":[0],"argument":[1,100,151],"extraction":[2],"identifies":[3],"arguments":[4,21,62,68],"for":[5,29,36,77,97],"predefined":[6],"event":[7,99],"roles":[8],"in":[9],"text.Existing":[10],"work":[11],"evaluates":[12],"this":[13,32,88],"task":[14],"with":[15,25,114,147],"exact":[16],"match":[17],"(EM),":[18],"where":[19],"predicted":[20],"must":[22],"align":[23,113],"exactly":[24],"annotated":[26],"spans.While":[27],"suitable":[28],"spanbased":[30],"models,":[31],"approach":[33],"falls":[34],"short":[35],"large":[37],"language":[38],"models":[39],"(LLMs),":[40],"which":[41],"often":[42],"generate":[43],"diverse":[44],"yet":[45],"semantically":[46],"accurate":[47],"arguments.EM":[48],"severely":[49],"underestimates":[50],"performance":[51,126],"by":[52,136],"disregarding":[53],"valid":[54],"variations.Furthermore,":[55],"EM":[56],"evaluation":[57,79],"fails":[58],"to":[59,111],"capture":[60],"implicit":[61],"(unstated":[63],"but":[64],"inferable)":[65],"and":[66,108],"scattered":[67],"(distributed":[69],"across":[70],"a":[71,93],"document).These":[72],"limitations":[73],"underscore":[74],"the":[75,103],"need":[76],"an":[78,124],"framework":[80,96],"that":[81,121],"better":[82,112],"captures":[83],"models'":[84],"actual":[85],"performance.To":[86],"bridge":[87],"gap,":[89],"we":[90],"introduce":[91],"REGen,":[92],"Reliable":[94],"Evaluation":[95],"Generative":[98],"extraction.REGen":[101],"combines":[102],"strengths":[104],"of":[105,128,150],"exact,":[106],"relaxed,":[107],"LLM-based":[109],"matching":[110],"human":[115,148],"judgment.Experiments":[116],"on":[117],"six":[118],"datasets":[119],"show":[120],"REGen":[122],"reveals":[123],"average":[125],"gain":[127],"+23.93":[129],"F1":[130],"over":[131],"EM,":[132],"reflecting":[133],"capabilities":[134],"overlooked":[135],"prior":[137],"evaluation.Human":[138],"validation":[139],"further":[140],"confirms":[141],"REGen's":[142],"effectiveness,":[143],"achieving":[144],"87.67%":[145],"alignment":[146],"assessments":[149],"correctness.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}