{"id":"https://openalex.org/W4416036725","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.328","title":"AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment","display_name":"AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036725","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.328"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.328","pdf_url":"https://aclanthology.org/2025.emnlp-main.328.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.328.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113354569","display_name":"Mengyu Bu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mengyu Bu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031466943","display_name":"Shaolei Zhang","orcid":"https://orcid.org/0000-0002-7254-9380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaolei Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100528467","display_name":"Zhongjun He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongjun He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112985399","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0001-8254-1561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101398253","display_name":"Yang Feng","orcid":"https://orcid.org/0000-0001-7362-9844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Feng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113354569"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17541275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6471","last_page":"6500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3294999897480011,"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":0.3294999897480011,"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":0.24500000476837158,"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":0.051600001752376556,"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/representation","display_name":"Representation (politics)","score":0.507099986076355},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.35429999232292175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3276999890804291},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3061999976634979},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30489999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142999887466431},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.507099986076355},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4731999933719635},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.328","pdf_url":"https://aclanthology.org/2025.emnlp-main.328.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.328","pdf_url":"https://aclanthology.org/2025.emnlp-main.328.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036725.pdf","grobid_xml":"https://content.openalex.org/works/W4416036725.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"large":[1],"language":[2,89],"models":[3],"(LLMs)":[4],"possess":[5],"impressive":[6],"multilingual":[7,33,61,72,82,85,98,103,117,129],"understanding":[8],"and":[9,14,30,43,88,119,132],"generation":[10,121],"capabilities.However,":[11],"their":[12],"performance":[13,62,73],"cross-lingual":[15,120,135],"alignment":[16,42,87],"often":[17,38],"lag":[18],"for":[19,70],"non-dominant":[20],"languages.A":[21],"common":[22],"solution":[23],"is":[24,65],"to":[25,40,58],"fine-tune":[26],"LLMs":[27,101,110],"on":[28,107],"largescale":[29],"more":[31],"balanced":[32],"corpora,":[34],"but":[35],"such":[36],"approaches":[37],"lead":[39],"imprecise":[41],"suboptimal":[44],"knowledge":[45],"transfer,":[46],"struggling":[47],"with":[48,84],"limited":[49],"improvements":[50],"across":[51],"languages.In":[52],"this":[53],"paper,":[54],"we":[55,80,95],"propose":[56],"AlignX":[57,126],"bridge":[59],"the":[60,77,92,97,128,134],"gap,":[63],"which":[64],"a":[66],"two-stage":[67],"representationlevel":[68],"framework":[69],"enhancing":[71],"of":[74,100],"pre-trained":[75,109],"LLMs.In":[76],"first":[78],"stage,":[79,94],"align":[81],"representations":[83,130],"semantic":[86],"feature":[90],"integration.In":[91],"second":[93],"stimulate":[96],"capability":[99],"via":[102],"instruction":[104],"fine-tuning.Experimental":[105],"results":[106],"several":[108],"demonstrate":[111],"that":[112,125],"our":[113],"approach":[114],"enhances":[115],"LLMs'":[116],"general":[118],"capability.Further":[122],"analysis":[123],"indicates":[124],"brings":[127],"closer":[131],"improves":[133],"alignment.":[136]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}