{"id":"https://openalex.org/W4412889393","doi":"https://doi.org/10.18653/v1/2025.acl-srw.95","title":"Testing English News Articles for Lexical Homogenization Due to Widespread Use of Large Language Models","display_name":"Testing English News Articles for Lexical Homogenization Due to Widespread Use of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889393","doi":"https://doi.org/10.18653/v1/2025.acl-srw.95"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-srw.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.95","pdf_url":"https://aclanthology.org/2025.acl-srw.95.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-srw.95.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181749","display_name":"Sarah Fitterer","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sarah Fitterer","raw_affiliation_strings":["Technische Universitt Berlin Berlin , Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universitt Berlin Berlin , Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181750","display_name":"Dominik Gangl","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Gangl","raw_affiliation_strings":["Technische Universitt Berlin Berlin , Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universitt Berlin Berlin , Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119181751","display_name":"Jannes Ulbrich","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jannes Ulbrich","raw_affiliation_strings":["Technische Universitt Berlin Berlin , Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universitt Berlin Berlin , Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119181749"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10788624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1239","last_page":"1245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9172999858856201,"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":0.9172999858856201,"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/computer-science","display_name":"Computer science","score":0.6911076307296753},{"id":"https://openalex.org/keywords/homogenization","display_name":"Homogenization (climate)","score":0.4952053129673004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49063506722450256},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.44200438261032104},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.4108476936817169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40684449672698975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6911076307296753},{"id":"https://openalex.org/C2778722038","wikidata":"https://www.wikidata.org/wiki/Q17030643","display_name":"Homogenization (climate)","level":3,"score":0.4952053129673004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49063506722450256},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44200438261032104},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.4108476936817169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40684449672698975},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-srw.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.95","pdf_url":"https://aclanthology.org/2025.acl-srw.95.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-srw.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.95","pdf_url":"https://aclanthology.org/2025.acl-srw.95.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889393.pdf","grobid_xml":"https://content.openalex.org/works/W4412889393.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2104620528","https://openalex.org/W140119233","https://openalex.org/W2757910772","https://openalex.org/W4249473811","https://openalex.org/W2394422079","https://openalex.org/W1492688905","https://openalex.org/W2524071042","https://openalex.org/W2550220886","https://openalex.org/W2025913943","https://openalex.org/W3204019825"],"abstract_inverted_index":{"It":[0],"is":[1,114],"widely":[2],"assumed":[3],"that":[4,40,111],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"are":[9,32],"shaping":[10],"language,":[11],"with":[12],"multiple":[13],"studies":[14,144],"noting":[15],"the":[16,77,85,130,146],"growing":[17],"presence":[18],"of":[19,46,118,148],"LLM-generated":[20],"content":[21],"and":[22,58,80,83,96,104],"suggesting":[23],"homogenizing":[24],"effects.However,":[25],"it":[26],"remains":[27],"unclear":[28],"if":[29],"these":[30],"effects":[31,125],"already":[33],"evident":[34],"in":[35,72,102,107,129,142],"recent":[36],"writing.This":[37],"study":[38],"addresses":[39],"gap":[41],"by":[42,76],"comparing":[43],"two":[44],"datasets":[45],"English":[47],"online":[48,122],"news":[49],"articles":[50],"-one":[51],"from":[52,60],"2018,":[53],"prior":[54],"to":[55,89,134,138],"LLM":[56,64,91,149],"popularization,":[57],"one":[59],"2024,":[61],"after":[62],"widespread":[63],"adoption.We":[65],"define":[66],"lexical":[67,73,140],"homogenization":[68,124,141],"as":[69],"a":[70],"decrease":[71],"diversity,":[74],"measured":[75],"MATTR,":[78],"Maas,":[79],"MTLD":[81,95],"metrics,":[82],"introduce":[84],"LLM-Style-Word":[86],"Ratio":[87],"(SWR)":[88],"measure":[90,139],"influence.We":[92],"found":[93],"higher":[94],"SWR":[97],"scores,":[98],"yet":[99],"negligible":[100],"changes":[101],"Maas":[103],"MATTR":[105],"scores":[106],"2024":[108],"corpus.We":[109],"conclude":[110],"while":[112],"there":[113],"an":[115],"apparent":[116],"influence":[117,147],"LLMs":[119],"on":[120,145,151],"written":[121],"English,":[123],"do":[126],"not":[127],"show":[128],"measurements.We":[131],"therefore":[132],"propose":[133],"apply":[135],"different":[136],"metrics":[137],"future":[143],"usage":[150],"language":[152],"change.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
