{"id":"https://openalex.org/W7140106402","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.13","title":"Stylistic Transfer from Annotator Communities to Large Language Models","display_name":"Stylistic Transfer from Annotator Communities to Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140106402","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.13"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.13","pdf_url":"https://aclanthology.org/2026.latechclfl-1.13.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.13.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130349600","display_name":"Jay Chooi","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jay Chooi","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5130349600"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30112549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.36820000410079956,"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":0.36820000410079956,"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":0.22699999809265137,"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/T12031","display_name":"Speech and dialogue systems","score":0.08829999715089798,"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/transfer","display_name":"Transfer (computing)","score":0.3763999938964844},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36419999599456787},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3068000078201294},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2775999903678894},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.26159998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043999791145325},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5435000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24079999327659607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.13","pdf_url":"https://aclanthology.org/2026.latechclfl-1.13.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.13","pdf_url":"https://aclanthology.org/2026.latechclfl-1.13.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 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4327850639820099,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140106402.pdf","grobid_xml":"https://content.openalex.org/works/W7140106402.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,22,178],"models":[2,23,39,141],"(LLMs)":[3],"are":[4,54],"posttrained":[5],"on":[6,21,86,176],"human":[7],"feedback":[8],"collected":[9],"from":[10,31,70,132],"annotator":[11,19,170,203],"communities,":[12],"yet":[13],"the":[14,28,35,57,80,83,87,115,125],"linguistic":[15,76,174,200],"influence":[16],"of":[17,38,59,82,95,165],"these":[18],"communities":[20,171],"remains":[24],"poorly":[25],"understood.We":[26],"investigated":[27],"stylistic":[29],"transfer":[30],"Nigerian":[32,96,122,133,149],"annotators":[33],"to":[34,111,153,159],"LLaMA":[36,45,48,116,126,139],"family":[37],"through":[40],"a":[41,60,155,185,199],"natural":[42],"experiment":[43],"with":[44,148,180,202],"2":[46,117,140],"and":[47,74,93,98],"3.1,":[49],"as":[50,162,184],"their":[51],"release":[52],"dates":[53],"separated":[55],"by":[56,78],"shutdown":[58],"major":[61],"data":[62],"annotation":[63],"service":[64],"provider":[65],"in":[66,146,191],"Nigeria.We":[67],"generated":[68],"corpora":[69,94],"both":[71,104,112],"model":[72,91,106,119,129],"families":[73],"measured":[75],"style":[77,175,201],"computing":[79],"difference-in-difference":[81],"Jensen-Shannon":[84],"distance":[85],"bigram":[88],"distribution":[89],"between":[90],"outputs":[92],"English":[97,113,150],"US":[99],"English.We":[100],"found":[101,136],"that,":[102],"although":[103],"pre-trained":[105],"variants":[107],"exhibit":[108],"similar":[109],"proximity":[110],"variants,":[114],"post-trained":[118,128,138],"moved":[120,130],"toward":[121],"English,":[123],"while":[124],"3.1":[127],"away":[131],"English.Qualitatively,":[134],"we":[135],"that":[137,169],"used":[142],"significantly":[143],"fewer":[144],"contractions,":[145],"line":[147],"speakers":[151],"opting":[152],"use":[154],"formal":[156],"register":[157],"due":[158],"its":[160],"role":[161],"an":[163],"index":[164],"knowledgeability.Our":[166],"findings":[167],"suggest":[168],"can":[172],"imprint":[173],"large":[177],"models,":[179],"potential":[181],"implications":[182],"such":[183],"disproportionately":[186],"higher":[187],"false":[188],"positive":[189],"rate":[190],"AI":[192],"plagiarism":[193],"detection":[194],"for":[195],"users":[196],"who":[197],"share":[198],"communities.":[204]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2026-03-24T00:00:00"}