{"id":"https://openalex.org/W7208747709","doi":"https://doi.org/10.48550/arxiv.2609.03577","title":"Language, Language Models, and What We're Talking About","display_name":"Language, Language Models, and What We're Talking About","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208747709","doi":"https://doi.org/10.48550/arxiv.2609.03577"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03577","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03577","pdf_url":"https://arxiv.org/pdf/2609.03577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.03577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114633633","display_name":"Malvina Nissim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Nissim, Malvina","raw_affiliation_strings":["University of Groningen , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen , The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5114633633"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9458000063896179,"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":0.9458000063896179,"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":0.024000000208616257,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.9750000238418579},{"id":"https://openalex.org/keywords/italian-language","display_name":"Italian language","score":0.7120000123977661},{"id":"https://openalex.org/keywords/training-data","display_name":"training data","score":0.5320000052452087},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.9879999756813049},{"id":"https://openalex.org/keywords/linguistic-diversity","display_name":"linguistic diversity","score":0.5049999952316284},{"id":"https://openalex.org/keywords/meaning-of-language","display_name":"meaning of language","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5828999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5174999833106995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31060001254081726},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.27970001101493835},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C24570573","wikidata":"https://www.wikidata.org/wiki/Q7191197","display_name":"Picture language","level":5,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.03577","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03577","pdf_url":"https://arxiv.org/pdf/2609.03577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.03577","doi":"https://doi.org/10.48550/arxiv.2609.03577","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03577","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03577","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03577","pdf_url":"https://arxiv.org/pdf/2609.03577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208747709.pdf","grobid_xml":"https://content.openalex.org/works/W7208747709.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412944107","https://openalex.org/W4417291044","https://openalex.org/W7196945227","https://openalex.org/W7062408702","https://openalex.org/W3202903412","https://openalex.org/W6968276150","https://openalex.org/W4312691188","https://openalex.org/W2120163746","https://openalex.org/W7214670548","https://openalex.org/W7165629692"],"abstract_inverted_index":{"Language":[0],"models":[1,26,46,70,75,98,120,127],"are":[2,10,144],"commonly":[3],"discussed":[4],"as":[5,27,122,129,156,158],"technical":[6,123],"artefacts,":[7],"but":[8],"they":[9,74],"obviously":[11],"shaped":[12],"by":[13,18],"the":[14,35,38,58,141,151],"linguistic":[15],"worlds":[16],"conveyed":[17],"data":[19],"during":[20],"their":[21],"training.":[22],"Using":[23],"Italian":[24],"language":[25,92,97,119,126,133],"evidence,":[28],"I":[29,101],"want":[30,96],"to":[31,34,57,99],"bring":[32],"attention":[33],"nature":[36],"of":[37,60,71,76],"systems":[39],"which":[40],"result":[41],"from":[42],"training":[43],"and":[44,49,52,56,125,150],"specialising":[45],"on":[47,63],"translated":[48],"synthetic":[50],"data,":[51],"further":[53],"curating":[54],"them,":[55],"meaning":[59],"testing":[61],"them":[62],"equally":[64],"unnatural":[65],"data.":[66],"Are":[67,73],"these":[68],"eventually":[69],"Italian?":[72],"language?":[77,83],"Does":[78],"NLP":[79],"still":[80],"care":[81],"about":[82,146],"These":[84],"questions":[85],"yield":[86],"another,":[87],"more":[88],"concrete":[89],"question:":[90],"what":[91],"do":[93,111],"we":[94,110,143,159],"actually":[95],"produce?":[100],"argue":[102],"that":[103],"this":[104],"question":[105],"cannot":[106],"be":[107,139,148,155],"answered":[108],"if":[109],"not":[112,154],"first":[113],"consider":[114],"a":[115],"clearer":[116],"distinction":[117],"between":[118],"designed":[121,128],"products":[124],"tools":[130],"for":[131],"studying":[132],"itself.":[134],"The":[135],"answers":[136],"then":[137],"might":[138,147,153],"diverse,":[140,149],"languages":[142],"talking":[145],"picture":[152],"pessimistic":[157],"fear.":[160]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-05T00:00:00"}