{"id":"https://openalex.org/W7166813590","doi":"https://doi.org/10.18653/v1/2026.acl-long.130","title":"ALIGN: Word Association Learning for Cultural Alignment in Large Language Models","display_name":"ALIGN: Word Association Learning for Cultural Alignment in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813590","doi":"https://doi.org/10.18653/v1/2026.acl-long.130"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.130","pdf_url":"https://aclanthology.org/2026.acl-long.130.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.130.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139786640","display_name":"Chunhua Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhua Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090317178","display_name":"Kabir Manandhar Shrestha","orcid":"https://orcid.org/0009-0001-2059-1683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kabir Manandhar Shrestha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108839886","display_name":"Sukai Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sukai Huang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80325035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2857","last_page":"2879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.36730000376701355,"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":0.36730000376701355,"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/T12090","display_name":"Language and cultural evolution","score":0.2282000035047531,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13510000705718994,"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/word","display_name":"Word (group theory)","score":0.454800009727478},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3986999988555908},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3100000023841858},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3091000020503998},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.30230000615119934},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.2921999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5879999995231628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5353999733924866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006999969482422},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27869999408721924},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.130","pdf_url":"https://aclanthology.org/2026.acl-long.130.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.130","pdf_url":"https://aclanthology.org/2026.acl-long.130.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813590.pdf","grobid_xml":"https://content.openalex.org/works/W7166813590.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,149],"(LLMs)":[3],"exhibit":[4],"cultural":[5,14,22,55,82,96,118,187],"bias":[6],"from":[7,60],"over-represented":[8],"viewpoints":[9],"in":[10,63,107,182,185,189],"training":[11],"data,":[12],"yet":[13],"alignment":[15,83,98,109,139,166,188],"remains":[16],"a":[17,25,34,85,121,158],"challenge":[18],"due":[19],"to":[20],"limited":[21],"knowledge":[23],"and":[24,36,67,73,77,94,116,128,175],"lack":[26],"of":[27,123,161],"exploration":[28],"into":[29],"effective":[30],"learning":[31],"approaches.We":[32],"introduce":[33],"cost-efficient":[35],"cognitively":[37],"grounded":[38,181],"method:":[39],"fine-tuning":[40,76],"LLMs":[41],"on":[42,114],"native":[43,61],"speakers'":[44],"word-association":[45],"norms,":[46],"leveraging":[47],"cognitive":[48],"psychology":[49],"findings":[50],"that":[51,89,157],"such":[52],"associations":[53,93,163],"capture":[54],"knowledge.Using":[56],"word":[57],"association":[58],"datasets":[59],"speakers":[62],"the":[64,100,173,176],"US":[65,127],"(English)":[66],"China":[68],"(Mandarin),":[69],"we":[70],"train":[71],"Llama-3.1-8B":[72],"Qwen-2.5-7Bvia":[74],"supervised":[75],"preference":[78],"optimization.We":[79],"evaluate":[80],"models'":[81],"through":[84],"two-tier":[86],"evaluation":[87],"framework":[88],"spans":[90],"low-level":[91],"lexical":[92,108],"high-level":[95,117],"value":[97,119,165],"using":[99],"World":[101],"Values":[102],"Survey.Results":[103],"show":[104],"significant":[105],"improvements":[106],"(16-20%":[110],"English,":[111],"43-165%":[112],"Mandarin":[113],"Precision@5)":[115],"shifts.On":[120],"subset":[122],"50":[124],"questions":[125],"where":[126],"Chinese":[129,141],"respondents":[130],"diverge":[131],"most,":[132],"finetuned":[133],"Qwen":[134],"nearly":[135],"doubles":[136],"its":[137],"response":[138],"with":[140],"values":[142],"(13":[143],"\u2192":[144],"25).Remarkably,":[145],"our":[146],"trained":[147],"7-8B":[148],"match":[150],"or":[151],"exceed":[152],"vanilla":[153],"70B":[154],"baselines,":[155],"demonstrating":[156],"few":[159],"million":[160],"culture-grounded":[162],"achieve":[164],"without":[167],"expensive":[168],"retraining.Our":[169],"work":[170],"highlights":[171],"both":[172],"promise":[174],"need":[177],"for":[178],"future":[179],"research":[180],"human":[183],"cognition":[184],"improving":[186],"AI":[190],"models.":[191]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}