{"id":"https://openalex.org/W7106340822","doi":"https://doi.org/10.1162/tacl.a.47","title":"Benchmarking Linguistic Diversity of Large Language Models","display_name":"Benchmarking Linguistic Diversity of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7106340822","doi":"https://doi.org/10.1162/tacl.a.47"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.47","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.47","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.47/2566986/tacl.a.47.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.47/2566986/tacl.a.47.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanzhu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yanzhu Guo","raw_affiliation_strings":["ALMAnaCH, Inria Paris, France. yanzhu.guo@inria.fr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH, Inria Paris, France. yanzhu.guo@inria.fr","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guokan Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I4405260733","display_name":"Institut fran\u00e7ais de la mode","ror":"https://ror.org/046p4xg50","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405260733"]}],"countries":["AE","FR"],"is_corresponding":false,"raw_author_name":"Guokan Shang","raw_affiliation_strings":["IFM Paris, MBZUAI, France. guokan.shang@mbzuai.ac.ae"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFM Paris, MBZUAI, France. guokan.shang@mbzuai.ac.ae","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I4405260733"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chlo\u00e9 Clavel","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chlo\u00e9 Clavel","raw_affiliation_strings":["ALMAnaCH, Inria Paris, France. chloe.clavel@inria.fr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH, Inria Paris, France. chloe.clavel@inria.fr","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8587,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98575726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"13","issue":null,"first_page":"1507","last_page":"1526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.17839999496936798,"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":0.17839999496936798,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.12700000405311584,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/diversity","display_name":"Diversity (politics)","score":0.5767999887466431},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5720000267028809},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5404999852180481},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.477400004863739},{"id":"https://openalex.org/keywords/raising","display_name":"Raising (metalworking)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42570000886917114},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.3783999979496002},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35679998993873596},{"id":"https://openalex.org/keywords/linguistic-description","display_name":"Linguistic description","score":0.35010001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354000210762024},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5756999850273132},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5720000267028809},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202000141143799},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C172205122","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic description","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2992249680","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Linguistic diversity","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C14919245","wikidata":"https://www.wikidata.org/wiki/Q1976109","display_name":"Language technology","level":4,"score":0.303600013256073},{"id":"https://openalex.org/C79078291","wikidata":"https://www.wikidata.org/wiki/Q980142","display_name":"Linguistic universal","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl.a.47","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.47","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.47/2566986/tacl.a.47.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05444994v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05444994","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, 2025, 13, pp.1507-1526. ⟨10.1162/TACL.a.47⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.47","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.47","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.47/2566986/tacl.a.47.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8505077958106995}],"awards":[{"id":"https://openalex.org/G5848506337","display_name":"Socio-Inspired Neural Networks for Conversational Systems","funder_award_id":"ANR-23-CE23-0033","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7106340822.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W52410547","https://openalex.org/W2001833328","https://openalex.org/W2014096218","https://openalex.org/W2029140263","https://openalex.org/W2122940614","https://openalex.org/W2257408573","https://openalex.org/W2317666317","https://openalex.org/W2605719446","https://openalex.org/W2787403940","https://openalex.org/W2963096510","https://openalex.org/W2970641574","https://openalex.org/W3034383590","https://openalex.org/W3037109418","https://openalex.org/W3100806282","https://openalex.org/W3105214104","https://openalex.org/W3117574848","https://openalex.org/W3155270181","https://openalex.org/W3173360659","https://openalex.org/W4287890952","https://openalex.org/W4385573550","https://openalex.org/W4385573686","https://openalex.org/W4385573874","https://openalex.org/W4388333192","https://openalex.org/W4389519097","https://openalex.org/W4389519254","https://openalex.org/W4389519362","https://openalex.org/W4391655440","https://openalex.org/W4394773742","https://openalex.org/W4399528455","https://openalex.org/W4401043297","https://openalex.org/W4402671236","https://openalex.org/W4402671286","https://openalex.org/W4402671302","https://openalex.org/W4402671696","https://openalex.org/W4404783440","https://openalex.org/W4404792934"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1],"development":[2],"and":[3,48,109,124,139],"evaluation":[4],"of":[5,39,43,50,58,70,74,142,148,156],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"has":[10],"primarily":[11],"focused":[12],"on":[13,152],"their":[14,149],"task-solving":[15],"capabilities,":[16],"with":[17],"recent":[18],"models":[19],"even":[20],"surpassing":[21],"human":[22,37,75],"performance":[23],"in":[24,41,85],"some":[25],"areas.":[26],"However,":[27],"this":[28,113],"focus":[29],"often":[30],"neglects":[31],"whether":[32,55],"machine-generated":[33],"language":[34,59,79],"matches":[35],"the":[36,56,68,72,82,136,145,153],"level":[38],"diversity,":[40],"terms":[42],"vocabulary":[44],"choice,":[45],"syntactic":[46,130],"construction,":[47],"expression":[49],"meaning,":[51],"raising":[52],"questions":[53],"about":[54],"fundamentals":[57],"generation":[60],"have":[61],"been":[62],"fully":[63],"addressed.":[64],"This":[65],"paper":[66],"emphasizes":[67],"importance":[69],"examining":[71],"preservation":[73],"linguistic":[76,103,146],"richness":[77],"by":[78,91],"models,":[80],"given":[81],"concerning":[83],"surge":[84],"online":[86],"content":[87],"produced":[88],"or":[89],"aided":[90],"LLMs.":[92],"We":[93],"adapt":[94],"a":[95],"comprehensive":[96],"framework":[97],"for":[98,129],"evaluating":[99],"LLMs":[100,119,143],"from":[101],"various":[102],"diversity":[104,122,147],"perspectives":[105],"including":[106],"lexical,":[107],"syntactic,":[108],"semantic":[110],"dimensions.":[111],"Using":[112],"framework,":[114],"we":[115,133],"benchmark":[116],"several":[117],"state-of-the-art":[118],"across":[120],"all":[121],"dimensions,":[123],"conduct":[125],"an":[126],"in-depth":[127],"analysis":[128],"diversity.":[131],"Finally,":[132],"analyze":[134],"how":[135],"design,":[137],"development,":[138],"deployment":[140],"choices":[141],"impact":[144],"outputs,":[150],"focusing":[151],"creative":[154],"task":[155],"story":[157],"generation.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":10}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-11-23T00:00:00"}