{"id":"https://openalex.org/W4416149684","doi":"https://doi.org/10.1162/tacl.a.793","title":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","display_name":"R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416149684","doi":"https://doi.org/10.1162/tacl.a.793"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.793","doi":"https://doi.org/10.1162/tacl.a.793","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.793","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl.a.793","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108150655","display_name":"M. He","orcid":"https://orcid.org/0009-0006-4719-6241","observed_orcids":["https://orcid.org/0009-0006-4719-6241"]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minggui He","raw_affiliation_strings":["Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yilun Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yilun Liu","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921","observed_orcids":["https://orcid.org/0000-0002-2795-6921"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043396134","display_name":"Hongyong Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyong Zeng","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149397151","display_name":"Jian Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392186","display_name":"Yuanchang Luo","orcid":"https://orcid.org/0009-0001-4411-462X","observed_orcids":["https://orcid.org/0009-0001-4411-462X"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchang Luo","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418950","display_name":"Zhang Li","orcid":"https://orcid.org/0000-0001-6674-692X","observed_orcids":["https://orcid.org/0000-0001-6674-692X","https://orcid.org/0000-0002-2258-5893"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012613066","display_name":"Daimeng Wei","orcid":"https://orcid.org/0009-0008-9606-5058","observed_orcids":["https://orcid.org/0009-0008-9606-5058"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027448460","display_name":"Weibin Meng","orcid":"https://orcid.org/0000-0002-9384-9016","observed_orcids":["https://orcid.org/0000-0002-9384-9016"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Meng","raw_affiliation_strings":["Huawei Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057487414","display_name":"Osamu Yoshie","orcid":"https://orcid.org/0000-0002-4192-554X","observed_orcids":["https://orcid.org/0000-0002-4192-554X"]},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Yoshie","raw_affiliation_strings":["Waseda University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01562329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"2103","last_page":"2119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9746000170707703,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9746000170707703,"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/T10028","display_name":"Topic Modeling","score":0.019600000232458115,"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/T10759","display_name":"Translation Studies and Practices","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.871999979019165},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6200000047683716},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/multilingual-translation","display_name":"multilingual translation","score":0.5820000171661377},{"id":"https://openalex.org/keywords/domain-specific-translation","display_name":"domain-specific translation","score":0.9210000038146973},{"id":"https://openalex.org/keywords/unseen-languages","display_name":"unseen languages","score":0.7680000066757202},{"id":"https://openalex.org/keywords/round-trip-translation","display_name":"round-trip translation","score":0.7459999918937683},{"id":"https://openalex.org/keywords/paraphrasing","display_name":"paraphrase","score":0.824999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357000112533569},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208999752998352},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6079999804496765},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4537000060081482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.36579999327659607},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl.a.793","doi":"https://doi.org/10.1162/tacl.a.793","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.793","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2502.19735","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.19735","pdf_url":"https://arxiv.org/pdf/2502.19735","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.19735","doi":"https://doi.org/10.48550/arxiv.2502.19735","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.19735","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.793","doi":"https://doi.org/10.1162/tacl.a.793","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.793","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-b","jufo-1","norway-2","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7129774844","https://openalex.org/W4416034211","https://openalex.org/W7154997007","https://openalex.org/W7204581007","https://openalex.org/W7140088321","https://openalex.org/W4416039519","https://openalex.org/W7172473878","https://openalex.org/W7170169905","https://openalex.org/W7163127149","https://openalex.org/W7213921792"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"recent":[2],"breakthroughs":[3],"in":[4,107,162],"reasoning-enhanced":[5],"large":[6],"language":[7],"models":[8],"(LLMs),":[9],"incorporating":[10],"inference-time":[11,82],"reasoning":[12,28,83],"into":[13],"application":[14],"tasks":[15],"such":[16],"as":[17],"machine":[18],"translation":[19,70,106,159,170],"(MT),":[20],"where":[21],"human":[22,130,151],"translators":[23],"naturally":[24],"employ":[25],"structured,":[26],"multi-layered":[27],"chain-of-thoughts":[29],"(CoTs),":[30],"is":[31],"yet":[32],"un-derexplored.":[33],"Existing":[34],"methods":[35],"either":[36],"design":[37],"a":[38,43,77,157,163],"fixed":[39],"CoT":[40,125],"tailored":[41],"for":[42,84],"specific":[44],"MT":[45,86,109,179],"sub-task":[46],"(e.g.,":[47,111],"literature":[48],"translation),":[49],"or":[50],"rely":[51],"on":[52,172,182],"synthesizing":[53],"CoTs":[54,93,143],"unaligned":[55],"with":[56,91],"humans":[57],"and":[58,135,138,152,168,176],"supervised":[59],"fine-tuning":[60],"(SFT)":[61],"prone":[62],"to":[63,68,80],"overfitting,":[64],"limiting":[65],"their":[66],"adaptability":[67],"diverse":[69],"scenarios.":[71],"This":[72],"paper":[73],"introduces":[74],"R1-Translator":[75],"(R1-T1),":[76],"novel":[78],"framework":[79],"achieve":[81],"general":[85],"via":[87],"reinforcement":[88],"learning":[89],"(RL)":[90],"human-aligned":[92],"comprising":[94],"six":[95,123],"common":[96],"patterns.":[97],"Our":[98],"approach":[99],"pioneers":[100],"three":[101],"innovations:":[102],"(1)":[103],"verifying":[104],"reasoning-based":[105],"various":[108],"scenarios":[110],"multilingual":[112],"MT,":[113],"domain":[114],"MT)":[115],"unseen":[116,185],"from":[117,186],"the":[118,183],"training":[119],"phase;":[120],"(2)":[121],"formalizing":[122],"expert-curated":[124],"templates":[126],"that":[127],"mirror":[128],"hybrid":[129],"strategies":[131],"like":[132],"context-aware":[133],"paraphrasing":[134],"round-trip":[136],"translation;":[137],"(3)":[139],"enabling":[140],"more":[141],"flexible":[142],"through":[144],"an":[145],"RL":[146],"stage":[147],"after":[148],"cold-start.":[149],"Both":[150],"automatic":[153],"evaluation":[154],"results":[155],"indicate":[156],"steady":[158],"quality":[160],"improvement":[161],"total":[164],"of":[165],"10+":[166],"languages":[167,184],"40+":[169],"directions":[171],"Flores-101":[173],"test":[174],"set":[175],"four":[177],"domain-specific":[178],"tasks,":[180],"especially":[181],"training.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2025-10-10T00:00:00"}