{"id":"https://openalex.org/W7166814632","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2100","title":"Prompt Optimization for Relation Extraction using Reinforcement Learning","display_name":"Prompt Optimization for Relation Extraction using Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166814632","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2100"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2100","pdf_url":"https://aclanthology.org/2026.findings-acl.2100.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139750605","display_name":"Ying Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Software College , Northeastern University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software College , Northeastern University , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736111","display_name":"Dong Shuai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105287708","display_name":"Zibo Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui Zibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062814209","display_name":"TengQi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118911","display_name":"META Group","ror":"https://ror.org/027ng0s03","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210118911"]},{"id":"https://openalex.org/I4210140397","display_name":"Metrica (United States)","ror":"https://ror.org/031ffw737","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140397"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"TengQi Ye","raw_affiliation_strings":["Meta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta , USA","institution_ids":["https://openalex.org/I4210118911","https://openalex.org/I4210140397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139752912","display_name":"Gang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Gang Wu","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , China","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":3,"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":0.77833363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42321","last_page":"42334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13670000433921814,"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":0.13670000433921814,"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":0.05299999937415123,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04430000111460686,"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/relation","display_name":"Relation (database)","score":0.5418999791145325},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4438000023365021},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.33889999985694885},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.27810001373291016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27399998903274536},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.27390000224113464}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5249000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31769999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2100","pdf_url":"https://aclanthology.org/2026.findings-acl.2100.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2100","pdf_url":"https://aclanthology.org/2026.findings-acl.2100.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166814632.pdf","grobid_xml":"https://content.openalex.org/works/W7166814632.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Relation":[0],"extraction":[1,126,142],"is":[2,38],"a":[3,32,54,69,80,90,104,113,120,134],"fundamental":[4],"task":[5],"in":[6,21],"information":[7],"extraction.Still,":[8],"existing":[9,156],"supervised":[10,160],"approaches":[11],"rely":[12],"heavily":[13],"on":[14,139],"largescale":[15],"annotated":[16],"data,":[17],"limiting":[18],"their":[19,36],"applicability":[20],"domain-specific":[22],"and":[23,49,85,103,128,148,159,167],"low-resource":[24],"scenarios.Prompt-based":[25],"methods":[26,158],"with":[27,79],"large":[28],"language":[29],"models":[30],"provide":[31],"parameter-efficient":[33],"alternative;":[34],"however,":[35],"performance":[37],"susceptible":[39],"to":[40,131],"prompt":[41,58,66,75,173],"design,":[42],"which":[43],"often":[44],"requires":[45],"extensive":[46],"domain":[47,62],"expertise":[48],"heuristic":[50],"trial-and-error.We":[51],"propose":[52],"REPO,":[53],"reinforcement":[55],"learning-based":[56],"automated":[57],"optimization":[59,174],"framework":[60,92],"for":[61],"relation":[63,141],"extraction.REPO":[64],"formulates":[65],"construction":[67],"as":[68,133],"structured,":[70],"sequential":[71],"decisionmaking":[72],"problem,":[73],"optimizing":[74],"quality":[76],"through":[77],"interaction":[78],"black-box":[81],"LLM.To":[82],"enable":[83],"efficient":[84],"stable":[86],"optimization,":[87],"we":[88],"introduce":[89],"two-stage":[91],"comprising":[93],"an":[94],"initial":[95],"prompt-construction":[96],"stage":[97,107],"that":[98,108,124,152],"generates":[99],"semantically":[100],"grounded":[101],"candidates":[102],"DRL-based":[105,172],"refinement":[106],"iteratively":[109],"improves":[110],"prompts":[111],"within":[112],"constrained,":[114],"domain-aware":[115],"action":[116],"space.We":[117],"further":[118,163],"design":[119],"composite":[121],"evaluation":[122],"metric":[123],"integrates":[125],"accuracy":[127],"semantic":[129],"consistency":[130],"serve":[132],"dense":[135],"reward":[136],"signal.Extensive":[137],"experiments":[138],"multiple":[140],"datasets":[143],"across":[144],"medical,":[145],"financial,":[146],"legal,":[147],"news":[149],"domains":[150],"demonstrate":[151],"REPO":[153],"consistently":[154],"outperforms":[155],"prompt-based":[157],"baselines.Ablation":[161],"studies":[162],"confirm":[164],"the":[165,170],"effectiveness":[166],"robustness":[168],"of":[169],"proposed":[171],"strategy.":[175]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2026-07-02T00:00:00"}