{"id":"https://openalex.org/W7166874418","doi":"https://doi.org/10.18653/v1/2026.acl-long.1587","title":"R1-RE: Cross-Domain Relation Extraction with RLVR","display_name":"R1-RE: Cross-Domain Relation Extraction with RLVR","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166874418","doi":"https://doi.org/10.18653/v1/2026.acl-long.1587"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1587","pdf_url":"https://aclanthology.org/2026.acl-long.1587.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1587.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139852918","display_name":"Runpeng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runpeng Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139780123","display_name":"Tong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848222","display_name":"Run Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Run Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053966492","display_name":"Kaixian Yu","orcid":"https://orcid.org/0000-0002-7016-206X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixian Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139799314","display_name":"Hongtu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongtu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.86307054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34387","last_page":"34401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.17069999873638153,"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":0.17069999873638153,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13269999623298645,"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":0.1225999966263771,"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/task","display_name":"Task (project management)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.583299994468689},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5480999946594238},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5443000197410583},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5343999862670898},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.4724000096321106},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45579999685287476},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6765000224113464},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4724000096321106},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C2780366209","wikidata":"https://www.wikidata.org/wiki/Q5170200","display_name":"Core model","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1587","pdf_url":"https://aclanthology.org/2026.acl-long.1587.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1587","pdf_url":"https://aclanthology.org/2026.acl-long.1587.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166874418.pdf","grobid_xml":"https://content.openalex.org/works/W7166874418.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Relation":[0],"extraction":[1],"(RE)":[2],"is":[3],"a":[4,16,44,93],"core":[5],"task":[6,46],"in":[7,79],"natural":[8],"language":[9,73],"processing.Traditional":[10],"approaches":[11],"typically":[12],"frame":[13],"RE":[14,42,64],"as":[15,43,114],"supervised":[17],"learning":[18,57],"problem,":[19],"directly":[20],"mapping":[21],"context":[22],"to":[23],"labels-an":[24],"approach":[25,86],"that":[26],"often":[27],"suffers":[28],"from":[29],"poor":[30],"out-of-domain":[31],"(OOD)":[32],"generalization.Inspired":[33],"by":[34,48],"the":[35,54,68,88,123,131],"workflow":[36],"of":[37,71,104,130],"human":[38],"annotators,":[39],"we":[40],"reframe":[41],"reasoning":[45,69,128],"guided":[47],"annotation":[49,76],"guidelines":[50],"and":[51,92,126],"introduce":[52],"R1-RE,":[53],"first":[55],"reinforcement":[56],"with":[58,109],"verifiable":[59],"reward":[60],"(RLVR)":[61],"framework":[62],"for":[63,75,134],"tasks.Our":[65],"method":[66],"elicits":[67],"abilities":[70],"small":[72],"models":[74,112],"tasks,":[77],"resulting":[78],"significantly":[80],"improved":[81],"OOD":[82,102],"robustness.We":[83],"evaluate":[84],"our":[85,116],"on":[87,107],"public":[89],"Sem-2010":[90],"dataset":[91],"private":[94],"MDKG":[95],"dataset.The":[96],"R1-RE-7B":[97],"model":[98],"attains":[99],"an":[100],"average":[101],"accuracy":[103],"approximately":[105],"70%,":[106],"par":[108],"leading":[110],"proprietary":[111],"such":[113],"GPT-4o.Additionally,":[115],"comprehensive":[117],"analysis":[118],"provides":[119],"novel":[120],"insights":[121],"into":[122],"training":[124],"dynamics":[125],"emergent":[127],"behaviors":[129],"RLVR":[132],"paradigm":[133],"RE.":[135],"1":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}