{"id":"https://openalex.org/W7130320810","doi":"https://doi.org/10.1109/bigdia68682.2025.11383212","title":"Focus, Attend, Extract: LLM-Guided Prompt Refinement for Event Argument Extraction","display_name":"Focus, Attend, Extract: LLM-Guided Prompt Refinement for Event Argument Extraction","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W7130320810","doi":"https://doi.org/10.1109/bigdia68682.2025.11383212"},"language":"en","primary_location":{"id":"doi:10.1109/bigdia68682.2025.11383212","doi":"https://doi.org/10.1109/bigdia68682.2025.11383212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdia68682.2025.11383212","pdf_url":null,"source":{"id":"https://openalex.org/S7407088196","display_name":"International Conference on Big Data and Information Analytics (BigDIA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Big Data and Information Analytics (BigDIA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102001024","display_name":"Zhenyu Song","orcid":"https://orcid.org/0000-0003-2386-2271","observed_orcids":["https://orcid.org/0000-0003-2386-2271"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Song","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157203003","display_name":"Shiyu Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Fang","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109727108","display_name":"Ningchao Ge","orcid":"https://orcid.org/0000-0003-3770-1217","observed_orcids":["https://orcid.org/0000-0003-3770-1217"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningchao Ge","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126285193","display_name":"Xuan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Li","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007692391","display_name":"Lihua Liu","orcid":"https://orcid.org/0000-0002-5774-951X","observed_orcids":["https://orcid.org/0000-0002-5774-951X"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Liu","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126297112","display_name":"Jiaxuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxuan Liu","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53643929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"675","last_page":"681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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":0.9901999831199646,"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":0.00430000014603138,"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":0.0013000000035390258,"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":1.0},{"id":"https://openalex.org/keywords/prompt-refinement","display_name":"prompt refinement","score":0.9160000085830688},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.906000018119812},{"id":"https://openalex.org/keywords/early-fusion","display_name":"feature-level fusion","score":0.7300000190734863},{"id":"https://openalex.org/keywords/role-classification","display_name":"role classification","score":0.38199999928474426},{"id":"https://openalex.org/keywords/event-participants","display_name":"event attendees","score":0.5350000262260437},{"id":"https://openalex.org/keywords/long-distance-dependencies","display_name":"long-distance dependencies","score":0.6480000019073486},{"id":"https://openalex.org/keywords/semantic-ambiguity","display_name":"semantic ambiguity","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875000238418579},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7121999859809875},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.6931999921798706},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.6779000163078308},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5360999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdia68682.2025.11383212","doi":"https://doi.org/10.1109/bigdia68682.2025.11383212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdia68682.2025.11383212","pdf_url":null,"source":{"id":"https://openalex.org/S7407088196","display_name":"International Conference on Big Data and Information Analytics (BigDIA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Big Data and Information Analytics (BigDIA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2983386625","https://openalex.org/W3102925419","https://openalex.org/W3170759063","https://openalex.org/W4221159406","https://openalex.org/W4225373045","https://openalex.org/W4287019595","https://openalex.org/W4385572665","https://openalex.org/W4387848836","https://openalex.org/W4389519890","https://openalex.org/W4389523859","https://openalex.org/W4393147108","https://openalex.org/W4402669934","https://openalex.org/W4402670367","https://openalex.org/W4402670546","https://openalex.org/W4402670900","https://openalex.org/W4402671778","https://openalex.org/W4402672030","https://openalex.org/W4402684024","https://openalex.org/W4409363628","https://openalex.org/W4409657473","https://openalex.org/W4411630332","https://openalex.org/W4412888229","https://openalex.org/W4412889958","https://openalex.org/W4412944522"],"related_works":["https://openalex.org/W4406461528","https://openalex.org/W6892083294","https://openalex.org/W7215087822","https://openalex.org/W4416250751","https://openalex.org/W4297778375","https://openalex.org/W4396528539","https://openalex.org/W4402953187","https://openalex.org/W4404400436","https://openalex.org/W4322631374","https://openalex.org/W7124462560"],"abstract_inverted_index":{"Event":[0],"Argument":[1],"Extraction":[2],"(EAE)":[3],"is":[4,102,142,161],"a":[5,61,97,117,162],"fundamental":[6],"information":[7,160],"extraction":[8],"task,":[9],"focuses":[10],"on":[11,35,122],"pinpointing":[12],"event":[13],"participants":[14],"and":[15,83,105],"categorizing":[16],"their":[17,33,40],"specific":[18],"roles.":[19],"While":[20],"prompt-based":[21],"methods":[22],"leveraging":[23,154],"Pre-trained":[24],"Language":[25,75],"Models":[26],"(PLMs)":[27],"have":[28],"set":[29],"high":[30],"performance":[31],"standards,":[32],"reliance":[34],"static,":[36],"predefined":[37],"prompts":[38,66],"limits":[39],"effectiveness":[41],"in":[42],"complex":[43],"scenarios":[44],"involving":[45],"long-distance":[46],"dependencies":[47],"or":[48],"semantic":[49],"ambiguity.":[50],"To":[51],"address":[52],"this,":[53],"we":[54,95],"propose":[55],"LLM-Enhanced":[56],"Focus":[57],"for":[58,90,165],"Prompts":[59],"(LEFP),":[60],"novel":[62],"framework":[63],"that":[64,127,139,153],"enhances":[65],"with":[67,107,177],"dynamic,":[68],"contextual":[69],"focus.":[70],"LEFP":[71,128],"employs":[72],"the":[73,80,85,108,113,172,178],"Large":[74],"Model":[76],"(LLM)":[77],"to":[78,156],"analyze":[79],"input":[81],"document":[82],"distill":[84],"most":[86],"salient":[87],"textual":[88,148],"evidence":[89],"each":[91],"argument":[92],"role,":[93],"which":[94],"term":[96],"\"focus":[98],"snippet\".":[99],"This":[100],"snippet":[101],"then":[103],"encoded":[104],"fused":[106],"original":[109],"role":[110],"representation":[111],"at":[112],"feature":[114],"level,":[115],"creating":[116],"context-aware":[118],"prompt.":[119],"Extensive":[120],"evaluation":[121],"three":[123],"challenging":[124],"datasets":[125],"indicates":[126],"consistently":[129],"improves":[130],"performance.":[131],"Further":[132],"ablation":[133],"studies":[134],"validate":[135],"our":[136],"design,":[137],"confirming":[138],"feature-level":[140],"fusion":[141],"significantly":[143],"more":[144],"effective":[145],"than":[146],"simple":[147],"concatenation.":[149],"Our":[150],"work":[151],"demonstrates":[152],"LLMs":[155,176],"generate":[157],"auxiliary":[158],"focus":[159],"promising":[163],"direction":[164],"enhancing":[166],"smaller,":[167],"specialized":[168],"models,":[169],"effectively":[170],"combining":[171],"reasoning":[173],"power":[174],"of":[175,180],"efficiency":[179],"fine-tuned":[181],"PLMs.":[182]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-19T00:00:00"}