{"id":"https://openalex.org/W4391894822","doi":"https://doi.org/10.1145/3639631.3639658","title":"Large Language Models Evaluate Machine Translation via Polishing","display_name":"Large Language Models Evaluate Machine Translation via Polishing","publication_year":2023,"publication_date":"2023-12-22","ids":{"openalex":"https://openalex.org/W4391894822","doi":"https://doi.org/10.1145/3639631.3639658"},"language":"en","primary_location":{"id":"doi:10.1145/3639631.3639658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639631.3639658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Algorithms Computing and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073659434","display_name":"Yiheng Wang","orcid":"https://orcid.org/0009-0002-2583-9235"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiheng Wang","raw_affiliation_strings":["Peking University, China"],"raw_orcid":"https://orcid.org/0009-0002-2583-9235","affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073659434"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"158","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9961000084877014,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9569000005722046,"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/machine-translation","display_name":"Machine translation","score":0.7459028363227844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7250311374664307},{"id":"https://openalex.org/keywords/polishing","display_name":"Polishing","score":0.7010849118232727},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.602830171585083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46131181716918945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4101426601409912},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14609339833259583},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.11882904171943665}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7459028363227844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250311374664307},{"id":"https://openalex.org/C138113353","wikidata":"https://www.wikidata.org/wiki/Q611639","display_name":"Polishing","level":2,"score":0.7010849118232727},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.602830171585083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46131181716918945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101426601409912},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14609339833259583},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.11882904171943665},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639631.3639658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639631.3639658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Algorithms Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2260677151","https://openalex.org/W2598654328","https://openalex.org/W2883386157","https://openalex.org/W2973065121","https://openalex.org/W4313122167","https://openalex.org/W4389519239","https://openalex.org/W4389519254","https://openalex.org/W4389520163"],"related_works":["https://openalex.org/W2355958986","https://openalex.org/W2775554247","https://openalex.org/W2883671469","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":{"Quality":[0],"of":[1,48,65,134,143],"machine":[2,81,125],"translation":[3,82],"is":[4,28,35],"usually":[5],"evaluated":[6],"by":[7,38,86],"automatic":[8],"reference-based":[9],"metrics.":[10],"However,":[11],"these":[12],"conventional":[13],"metrics":[14],"have":[15,59],"limited":[16],"correlation":[17],"with":[18,107,131,150],"human":[19,135,151],"evaluation":[20,27,64,83,110,152],"and":[21,41,53,112,139,163],"require":[22],"references":[23],"for":[24,62],"comparison.":[25],"Human":[26],"considered":[29],"the":[30,46,63,100,173],"most":[31],"reliable,":[32],"but":[33],"it":[34],"still":[36],"plagued":[37],"high":[39],"costs":[40],"uncertainties":[42],"among":[43],"annotators.":[44],"With":[45],"emergence":[47],"large":[49],"language":[50,67,121],"models":[51,122],"(LLMs)":[52],"their":[54],"impressive":[55],"capabilities,":[56],"some":[57],"studies":[58],"utilized":[60],"LLMs":[61,77,176],"natural":[66],"generation.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"EvLP":[74,106,147],"(Evaluation":[75],"via":[76],"Polishing),":[78],"a":[79,114,129,165],"reference-free":[80,116],"method":[84],"inspired":[85],"post-editing":[87],"that":[88,146,175],"leverages":[89],"LLMs.":[90],"We":[91,127,170],"select":[92,128],"gpt-3.5-turbo":[93],"to":[94,98,123,154],"act":[95],"as":[96],"annotators":[97],"polish":[99],"translated":[101],"text.":[102],"Our":[103],"experiments":[104,144],"compare":[105],"other":[108,155],"LLM-based":[109,156],"methods":[111],"SEG_LM,":[113],"representative":[115],"metric":[117],"utilizing":[118],"cross-lingual":[119],"pre-trained":[120],"evaluate":[124],"translation.":[126],"dataset":[130],"two":[132],"kinds":[133],"evaluation,":[136],"direct":[137,161],"assessment":[138,162],"post-editing.":[140,169],"The":[141],"results":[142],"demonstrate":[145],"closely":[148],"aligns":[149],"compared":[153],"metrics,":[157],"outperforming":[158],"SEG_LM":[159],"on":[160],"exhibiting":[164],"significant":[166],"advantage":[167],"in":[168],"also":[171],"discuss":[172],"bias":[174],"hold":[177],"towards":[178],"LLM-generated":[179],"texts.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}