{"id":"https://openalex.org/W4416034358","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1401","title":"CM-Align: Consistency-based Multilingual Alignment for Large Language Models","display_name":"CM-Align: Consistency-based Multilingual Alignment for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034358","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1401"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1401","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1401.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: EMNLP 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-emnlp.1401.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100445881","display_name":"Xue Zhang","orcid":"https://orcid.org/0000-0003-4279-899X"},"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/A5102206923","display_name":"Yunlong Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlong Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024849044","display_name":"Fandong Meng","orcid":"https://orcid.org/0000-0002-8158-2377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fandong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090423122","display_name":"Songming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394297","display_name":"Yufeng Chen","orcid":"https://orcid.org/0000-0003-0437-6788"},"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/A5101698034","display_name":"Jinan Xu","orcid":"https://orcid.org/0000-0003-0170-626X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100770464","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-5899-5165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhou","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25689","last_page":"25702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2863999903202057,"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":0.2863999903202057,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2222999930381775,"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/T13629","display_name":"Text Readability and Simplification","score":0.06759999692440033,"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/natural-language","display_name":"Natural language","score":0.34389999508857727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31029999256134033},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3043000102043152},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.2567000091075897},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2554999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829000115394592},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005000233650208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1401","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1401.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1401","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1401","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1401.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G106398601","display_name":null,"funder_award_id":"61976015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034358.pdf","grobid_xml":"https://content.openalex.org/works/W4416034358.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0,97],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"generally":[5],"show":[6],"a":[7,31,85,115],"significant":[8],"performance":[9],"gap":[10],"in":[11,28,38,58,64],"alignment":[12,72,93,129],"between":[13],"English":[14,29,77,137],"and":[15,69,83,140,151,158],"other":[16,39,95],"languages.To":[17],"bridge":[18],"this":[19],"gap,":[20],"existing":[21],"research":[22],"typically":[23],"leverages":[24],"the":[25,35,59,92,156,166],"model's":[26],"responses":[27,37,78],"as":[30],"reference":[32,138],"to":[33,105,120],"select":[34],"best/worst":[36],"languages,":[40],"which":[41,163],"are":[42,55,79],"then":[43],"used":[44],"for":[45,94,126],"Direct":[46],"Preference":[47],"Optimization":[48],"(DPO)":[49],"training.However,":[50],"we":[51,113],"argue":[52],"that":[53,62],"there":[54],"two":[56,134],"limitations":[57],"current":[60],"methods":[61,98],"result":[63],"noisy":[65],"multilingual":[66,107,123,128,143],"preference":[67,108,124,144,171],"data":[68,117,125,145],"further":[70,164],"limited":[71],"performance:":[73],"1)":[74],"Not":[75],"all":[76],"of":[80,160,168],"high":[81],"quality,":[82],"using":[84],"response":[86],"with":[87],"low":[88],"quality":[89],"may":[90],"mislead":[91],"languages.2)":[96],"usually":[99],"use":[100],"biased":[101],"or":[102],"heuristic":[103],"approaches":[104],"construct":[106,121],"pairs.To":[109],"address":[110],"these":[111],"limitations,":[112],"design":[114],"consistency-based":[116],"selection":[118,139],"method":[119,132],"high-quality":[122],"improving":[127],"(CM-Align).Specifically,":[130],"our":[131,161],"includes":[133],"parts:":[135],"consistency-guided":[136],"cross-lingual":[141],"consistencybased":[142],"construction.Experimental":[146],"results":[147],"on":[148],"three":[149,152],"LLMs":[150],"common":[153],"tasks":[154],"demonstrate":[155],"effectiveness":[157],"superiority":[159],"method,":[162],"indicates":[165],"necessity":[167],"constructing":[169],"highquality":[170],"data.":[172]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}