{"id":"https://openalex.org/W4392011835","doi":"https://doi.org/10.48550/arxiv.2402.11430","title":"EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models","display_name":"EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models","publication_year":2024,"publication_date":"2024-02-18","ids":{"openalex":"https://openalex.org/W4392011835","doi":"https://doi.org/10.48550/arxiv.2402.11430"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.11430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11430","pdf_url":"https://arxiv.org/pdf/2402.11430","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/2402.11430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068730597","display_name":"Jun Yao Gao","orcid":"https://orcid.org/0009-0006-6830-5849","observed_orcids":["https://orcid.org/0009-0006-6830-5849"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Jun","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101478660","display_name":"Huan Zhao","orcid":"https://orcid.org/0000-0002-0320-8718","observed_orcids":["https://orcid.org/0000-0002-0320-8718"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Huan","raw_affiliation_strings":["4Paradigm. Inc "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"4Paradigm. Inc ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391888","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-1568-2396","observed_orcids":["https://orcid.org/0000-0002-1568-2396","https://orcid.org/0000-0002-2908-3060","https://orcid.org/0000-0002-2772-4856","https://orcid.org/0009-0000-8893-8375","https://orcid.org/0000-0003-0264-788X","https://orcid.org/0000-0002-1717-5785","https://orcid.org/0000-0002-8180-2886","https://orcid.org/0000-0001-7608-7438","https://orcid.org/0000-0003-2262-2508"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":["Tsinghua University 4 HKUST , Hong Kong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University 4 HKUST , Hong Kong , China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102620271","display_name":"Changlong Yu","orcid":"https://orcid.org/0000-0002-4758-9014","observed_orcids":["https://orcid.org/0000-0002-4758-9014"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Changlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018149714","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0001-9885-2364","observed_orcids":["https://orcid.org/0000-0001-9885-2364"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Ruifeng","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9839000105857849,"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":0.9839000105857849,"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":0.007699999958276749,"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":0.0031999999191612005,"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-extraction","display_name":"event extraction","score":0.9940000176429749},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6439999938011169},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8569999933242798},{"id":"https://openalex.org/keywords/reward-function","display_name":"reward function","score":0.9679999947547913},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.6970000267028809},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.8640000224113464},{"id":"https://openalex.org/keywords/llama","display_name":"llamas","score":0.5680000185966492},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.8500000238418579},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.6800000071525574},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.8619999885559082},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.7707325220108032},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6103872060775757},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.589806079864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49904799461364746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40078532695770264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10215038061141968},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06696638464927673},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06494700908660889},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04993817210197449},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.11430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11430","pdf_url":"https://arxiv.org/pdf/2402.11430","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.2402.11430","doi":"https://doi.org/10.48550/arxiv.2402.11430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.11430","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:2402.11430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.11430","pdf_url":"https://arxiv.org/pdf/2402.11430","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392011835.pdf","grobid_xml":"https://content.openalex.org/works/W4392011835.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140161706","https://openalex.org/W7168402400","https://openalex.org/W4402684024","https://openalex.org/W7078600597","https://openalex.org/W7117158994","https://openalex.org/W7214342592","https://openalex.org/W4403331736","https://openalex.org/W4393147108","https://openalex.org/W7029732397","https://openalex.org/W4402953189"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"present":[4],"EventRL,":[5],"a":[6],"reinforcement":[7],"learning":[8],"approach":[9],"developed":[10],"to":[11,28,132,138,142],"enhance":[12],"event":[13,45,52,103,125],"extraction":[14],"for":[15,123],"large":[16],"language":[17],"models":[18],"(LLMs).":[19],"EventRL":[20,56,84],"utilizes":[21],"outcome":[22],"supervision":[23],"with":[24],"specific":[25],"reward":[26,112],"functions":[27],"tackle":[29],"prevalent":[30],"challenges":[31],"in":[32,94,100],"LLMs,":[33,73],"such":[34],"as":[35,41],"instruction":[36],"following":[37],"and":[38,47,67,77,96,115],"hallucination,":[39],"manifested":[40],"the":[42,48,92,108,117,136],"mismatch":[43],"of":[44,50,111,119],"structure":[46],"generation":[49],"undefined":[51],"types.":[53,104],"We":[54],"evaluate":[55],"against":[57],"existing":[58],"methods":[59],"like":[60],"Few-Shot":[61],"Prompting":[62],"(FSP)":[63],"(based":[64],"on":[65],"GPT4)":[66],"Supervised":[68],"Fine-Tuning":[69],"(SFT)":[70],"across":[71],"various":[72],"including":[74],"GPT-4,":[75],"LLaMa,":[76],"CodeLLaMa":[78],"models.":[79],"Our":[80],"findings":[81],"show":[82],"that":[83],"significantly":[85],"outperforms":[86],"these":[87],"conventional":[88],"approaches":[89],"by":[90],"improving":[91],"performance":[93],"identifying":[95],"structuring":[97],"events,":[98],"particularly":[99],"handling":[101],"novel":[102],"The":[105],"study":[106],"emphasizes":[107],"critical":[109],"role":[110],"function":[113],"selection":[114],"demonstrates":[116],"benefits":[118],"incorporating":[120],"code":[121],"data":[122],"better":[124],"extraction.":[126],"While":[127],"increasing":[128],"model":[129],"size":[130],"leads":[131],"higher":[133],"accuracy,":[134],"maintaining":[135],"ability":[137],"generalize":[139],"is":[140],"essential":[141],"avoid":[143],"overfitting.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-24T09:50:30.924529","created_date":"2024-02-22T00:00:00"}