{"id":"https://openalex.org/W7166838903","doi":"https://doi.org/10.18653/v1/2026.findings-acl.700","title":"Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation","display_name":"Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166838903","doi":"https://doi.org/10.18653/v1/2026.findings-acl.700"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.700","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.700","pdf_url":"https://aclanthology.org/2026.findings-acl.700.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.700.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139803501","display_name":"Rui Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847293","display_name":"Fengran Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengran Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719217","display_name":"Yufeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778306","display_name":"Xue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734037","display_name":"Shuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752483","display_name":"Hongliang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764339","display_name":"Jinan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Jinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139754113","display_name":"Meng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139749113","display_name":"Jian-Yun Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian-Yun Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139775113","display_name":"Kaiyu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyu Huang","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":0.828386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14291","last_page":"14310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.33070001006126404,"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":0.33070001006126404,"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":0.16519999504089355,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07840000092983246,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.3986999988555908},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3125999867916107},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.304500013589859},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3025999963283539},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.26570001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5411999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.700","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.700","pdf_url":"https://aclanthology.org/2026.findings-acl.700.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.700","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.700","pdf_url":"https://aclanthology.org/2026.findings-acl.700.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":[{"score":0.6962988376617432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G310944059","display_name":null,"funder_award_id":"62476023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5447623188","display_name":null,"funder_award_id":"62376019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5613447639","display_name":null,"funder_award_id":"2024JBGP008","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7838506768","display_name":null,"funder_award_id":"61976016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166838903.pdf","grobid_xml":"https://content.openalex.org/works/W7166838903.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"retrieval-augmented":[1],"generation":[2],"(MRAG)":[3],"requires":[4],"models":[5,52,114],"to":[6,54,101,115],"effectively":[7],"acquire":[8],"and":[9,38,57,89,105,142],"integrate":[10],"beneficial":[11],"external":[12],"knowledge":[13,55,103,118],"from":[14],"multilingual":[15,48,73],"collections.However,":[16],"most":[17],"existing":[18],"studies":[19],"employ":[20],"a":[21,35,41,72,80,147],"unitive":[22],"process":[23],"where":[24],"queries":[25],"of":[26,150],"equivalent":[27],"semantics":[28],"across":[29],"different":[30],"languages":[31],"are":[32],"processed":[33],"through":[34],"single-turn":[36],"retrieval":[37,143],"subsequent":[39],"optimization.Such":[40],"\"onesize-fits-all\"":[42],"strategy":[43],"is":[44,130,153],"often":[45],"suboptimal":[46],"in":[47,97,111],"settings,":[49],"as":[50,138],"the":[51,60,63,67,87,93,98,112,117],"occur":[53],"bias":[56],"conflict":[58],"during":[59],"interaction":[61],"with":[62],"search":[64],"engine.To":[65],"alleviate":[66],"issues,":[68],"we":[69],"propose":[70],"LCRL,":[71],"search-augmented":[74],"reinforcement":[75],"learning":[76],"framework":[77],"that":[78,122],"integrates":[79],"language-coupled":[81,94],"Group":[82],"Relative":[83],"Policy":[84],"Optimization":[85],"into":[86],"policy":[88],"reward":[90,113],"models.We":[91],"adopt":[92],"group":[95],"sampling":[96],"rollout":[99],"module":[100],"reduce":[102],"bias,":[104],"regularize":[106],"an":[107],"auxiliary":[108],"anti-consistency":[109],"penalty":[110],"mitigate":[116],"conflict.Experimental":[119],"results":[120],"demonstrate":[121],"LCRL":[123],"not":[124],"only":[125],"achieves":[126],"competitive":[127],"performance":[128],"but":[129],"also":[131],"appropriate":[132],"for":[133],"various":[134],"practical":[135],"scenarios":[136],"such":[137],"constrained":[139],"training":[140],"data":[141],"over":[144],"collections":[145],"encompassing":[146],"large":[148],"number":[149],"languages.Our":[151],"code":[152],"available":[154],"at":[155],"https:":[156],"//github.com/Cherry-qwq/LcRL-Open.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}