{"id":"https://openalex.org/W4412887886","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1045","title":"LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline","display_name":"LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887886","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1045"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1045","pdf_url":"https://aclanthology.org/2025.findings-acl.1045.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1045.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101417243","display_name":"Biao Fu","orcid":"https://orcid.org/0000-0002-4532-7432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biao Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073673415","display_name":"Minpeng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minpeng Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055225377","display_name":"Kai Fan","orcid":"https://orcid.org/0000-0002-8256-0807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074576488","display_name":"Chengxi Li","orcid":"https://orcid.org/0000-0003-1649-1943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengxi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425221","display_name":"Liang Zhang","orcid":"https://orcid.org/0000-0002-5172-4063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689058","display_name":"Yidong Chen","orcid":"https://orcid.org/0000-0002-0243-7228"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021246376","display_name":"Xiaodong Shi","orcid":"https://orcid.org/0000-0002-8163-7139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Shi","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":4.4761,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94707669,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"20372","last_page":"20395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9861999750137329,"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":0.9861999750137329,"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/computer-science","display_name":"Computer science","score":0.6760971546173096},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6461752653121948},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.569009006023407},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5602251291275024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21771883964538574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760971546173096},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6461752653121948},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.569009006023407},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5602251291275024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21771883964538574},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1045","pdf_url":"https://aclanthology.org/2025.findings-acl.1045.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1045","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1045","pdf_url":"https://aclanthology.org/2025.findings-acl.1045.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4107708189","display_name":null,"funder_award_id":"2022ZD0116101","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887886.pdf","grobid_xml":"https://content.openalex.org/works/W4412887886.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"When":[0],"the":[1,23,36,52,99,105,165,185],"complete":[2],"source":[3,37,106],"sentence":[4,25],"is":[5,49],"provided,":[6],"Large":[7],"Language":[8],"Models":[9],"(LLMs)":[10],"perform":[11],"excellently":[12],"in":[13,32,40,103],"offline":[14,75,169,186],"machine":[15,46],"translation":[16,47,187],"even":[17,149,183],"with":[18,92,150],"a":[19,41,79],"simple":[20],"prompt":[21],"\"Translate":[22],"following":[24],"from":[26],"[src":[27],"lang]":[28],"into":[29,112],"[tgt":[30],"lang]:\".However,":[31],"many":[33],"real":[34],"scenarios,":[35],"tokens":[38,109,119],"arrive":[39],"streaming":[42],"manner":[43],"and":[44,54,95,107,131,163],"simultaneous":[45],"(SiMT)":[48],"required,":[50],"then":[51],"efficiency":[53],"performance":[55,158],"of":[56,168],"decoder-only":[57],"LLMs":[58,67,127],"are":[59,110],"significantly":[60],"limited":[61,151],"by":[62,117],"their":[63],"auto-regressive":[64,144],"nature.To":[65],"enable":[66],"to":[68,121,128,175],"achieve":[69],"high-quality":[70],"SiMT":[71,161,177],"as":[72,74],"efficiently":[73],"translation,":[76],"we":[77],"propose":[78],"novel":[80],"paradigm":[81],"that":[82],"includes":[83],"constructing":[84],"supervised":[85],"fine-tuning":[86],"(SFT)":[87],"data":[88],"for":[89],"SiMT,":[90,104],"along":[91],"new":[93],"training":[94],"inference":[96],"strategies.To":[97],"replicate":[98],"token":[100],"input/output":[101],"stream":[102],"target":[108],"rearranged":[111],"an":[113],"interleaved":[114],"sequence,":[115],"separated":[116],"special":[118],"according":[120],"varying":[122,137],"latency":[123,138],"requirements.This":[124],"enables":[125],"powerful":[126],"learn":[129],"read":[130],"write":[132],"operations":[133],"adaptively,":[134],"based":[135],"on":[136],"prompts,":[139],"while":[140],"still":[141],"maintaining":[142],"efficient":[143],"decoding.Experimental":[145],"results":[146],"show":[147],"that,":[148],"SFT":[152],"data,":[153],"our":[154,171],"approach":[155,172],"achieves":[156],"stateof-the-art":[157],"across":[159],"various":[160],"benchmarks,":[162],"preserves":[164],"original":[166],"abilities":[167],"translation.Moreover,":[170],"generalizes":[173],"well":[174],"document-level":[176],"setting":[178],"without":[179],"requiring":[180],"specific":[181],"fine-tuning,":[182],"beyond":[184],"model":[188],"1":[189],".":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}