{"id":"https://openalex.org/W4395680645","doi":"https://doi.org/10.1162/tacl_a_00655","title":"Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions","display_name":"Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395680645","doi":"https://doi.org/10.1162/tacl_a_00655"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00655","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00655","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00655/2367429/tacl_a_00655.pdf","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,"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"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00655/2367429/tacl_a_00655.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101997858","display_name":"Jiahuan Li","orcid":"https://orcid.org/0000-0002-0016-7682"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahuan Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China lijh@smail.nju.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China lijh@smail.nju.edu.cn","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022574607","display_name":"Hao Zhou","orcid":"https://orcid.org/0000-0002-0173-0393"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China zhouh@smail.nju.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China zhouh@smail.nju.edu.cn","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102865824","display_name":"Shujian Huang","orcid":"https://orcid.org/0000-0003-4869-0832"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shujian Huang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China huangsj@nju.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China huangsj@nju.edu.cn","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046413480","display_name":"Shanbo Cheng","orcid":"https://orcid.org/0000-0002-6115-9483"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shanbo Cheng","raw_affiliation_strings":["Bytedance, China chengshanbo@bytedance.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance, China chengshanbo@bytedance.com","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427076","display_name":"Jiajun Chen","orcid":"https://orcid.org/0000-0001-5618-3932"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China chenjj@nju.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China chenjj@nju.edu.cn","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022574607","https://openalex.org/A5046413480","https://openalex.org/A5100427076","https://openalex.org/A5101997858","https://openalex.org/A5102865824"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":10.0025,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98508653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"576","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9907000064849854,"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/computer-science","display_name":"Computer science","score":0.8804599046707153},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.7697203159332275},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5355854630470276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5084144473075867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48382773995399475},{"id":"https://openalex.org/keywords/messenger-rna","display_name":"Messenger RNA","score":0.07417470216751099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804599046707153},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.7697203159332275},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5355854630470276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5084144473075867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48382773995399475},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.07417470216751099},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00655","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00655","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00655/2367429/tacl_a_00655.pdf","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,"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:doaj.org/article:b147a1f6cb204cb08e83fdc13617aca8","is_oa":true,"landing_page_url":"https://doaj.org/article/b147a1f6cb204cb08e83fdc13617aca8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00655","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00655","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00655/2367429/tacl_a_00655.pdf","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,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395680645.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2739967986","https://openalex.org/W2921280978","https://openalex.org/W2952153923","https://openalex.org/W2963532001","https://openalex.org/W2964073484","https://openalex.org/W3001279689","https://openalex.org/W3017454464","https://openalex.org/W3093871477","https://openalex.org/W3105425516","https://openalex.org/W3152788712","https://openalex.org/W3168413009","https://openalex.org/W3168867926","https://openalex.org/W3169369929","https://openalex.org/W3170611326","https://openalex.org/W3173647317","https://openalex.org/W4285077564","https://openalex.org/W4292779060","https://openalex.org/W4307079201","https://openalex.org/W4311642023","https://openalex.org/W4317547647","https://openalex.org/W4319323306","https://openalex.org/W4320167623","https://openalex.org/W4321472057","https://openalex.org/W4322718191","https://openalex.org/W4377297670","https://openalex.org/W4385565879","https://openalex.org/W4385571124","https://openalex.org/W4385571264","https://openalex.org/W4385572225","https://openalex.org/W4401042993","https://openalex.org/W6631190155","https://openalex.org/W6760411109","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6784447870","https://openalex.org/W6800875267","https://openalex.org/W6847076894","https://openalex.org/W6847118041","https://openalex.org/W6849563483","https://openalex.org/W6849733863","https://openalex.org/W6850105589","https://openalex.org/W6850182213","https://openalex.org/W6850625674","https://openalex.org/W6852005035","https://openalex.org/W6852449896"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Large-scale":[1],"pretrained":[2,54],"language":[3,55,143],"models":[4],"(LLMs),":[5],"such":[6],"as":[7],"ChatGPT":[8],"and":[9,91,119],"GPT4,":[10],"have":[11,71],"shown":[12],"strong":[13],"abilities":[14,74],"in":[15,97],"multilingual":[16,53,60,69,126],"translation,":[17],"without":[18],"being":[19],"explicitly":[20],"trained":[21],"on":[22,86,113],"parallel":[23],"corpora.":[24],"It":[25],"is":[26],"intriguing":[27],"how":[28],"the":[29,82,92,98,114,120,136,147],"LLMs":[30,70,131],"obtain":[31],"their":[32],"ability":[33,106],"to":[34,58,89,107,134],"carry":[35,108],"out":[36,109],"translation":[37,61,73,83,110,117,129,137],"instructions":[38,111,118],"for":[39,141],"different":[40,123],"languages.":[41,124],"In":[42],"this":[43],"paper,":[44],"we":[45,66,102],"present":[46],"a":[47,52,79],"detailed":[48],"analysis":[49],"by":[50],"finetuning":[51,127],"model,":[56],"XGLM-7.5B,":[57],"perform":[59,135],"following":[62],"given":[63],"instructions.":[64],"Firstly,":[65],"show":[67],"that":[68,104],"stronger":[72],"than":[75],"previously":[76],"demonstrated.":[77],"For":[78],"certain":[80],"language,":[81],"performance":[84],"depends":[85],"its":[87],"similarity":[88],"English":[90],"amount":[93],"of":[94,116],"data":[95],"used":[96],"pretraining":[99],"phase.":[100,150],"Secondly,":[101],"find":[103],"LLMs\u2019":[105],"relies":[112],"understanding":[115],"alignment":[121],"among":[122],"With":[125],"with":[128],"instructions,":[130],"could":[132],"learn":[133],"task":[138],"well":[139],"even":[140],"those":[142],"pairs":[144],"unseen":[145],"during":[146],"instruction":[148],"tuning":[149]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}