{"id":"https://openalex.org/W7140087641","doi":"https://doi.org/10.18653/v1/2026.eacl-long.55","title":"Lexical Popularity: Quantifying the Impact of Pre-training for LLM Performance","display_name":"Lexical Popularity: Quantifying the Impact of Pre-training for LLM Performance","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140087641","doi":"https://doi.org/10.18653/v1/2026.eacl-long.55"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.55","doi":"https://doi.org/10.18653/v1/2026.eacl-long.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.55","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2026.eacl-long.55","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069914401","display_name":"Elena Sofia Ruzzetti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Sofia Ruzzetti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029654514","display_name":"Fabio Massimo Zanzotto","orcid":"https://orcid.org/0000-0002-7301-3596","observed_orcids":["https://orcid.org/0000-0002-7301-3596"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabio Massimo Zanzotto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064384923","display_name":"Tommaso Caselli","orcid":"https://orcid.org/0000-0003-2936-0256","observed_orcids":["https://orcid.org/0000-0003-2936-0256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tommaso Caselli","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14508563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1209","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7651000022888184,"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":0.7651000022888184,"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":0.21879999339580536,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0024999999441206455,"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/pretraining","display_name":"pre-training","score":0.675000011920929},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9580000042915344},{"id":"https://openalex.org/keywords/word-frequency","display_name":"word frequency","score":0.6010000109672546},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23489999771118164},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22310000658035278},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2175000011920929}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.55","doi":"https://doi.org/10.18653/v1/2026.eacl-long.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.55","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire/f1320298-2662-402f-83d3-78b45f758255","doi":null,"is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/f1320298-2662-402f-83d3-78b45f758255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.55","doi":"https://doi.org/10.18653/v1/2026.eacl-long.55","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.55","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3175394187","https://openalex.org/W4412888163","https://openalex.org/W4416037039","https://openalex.org/W4385573037","https://openalex.org/W4407184767","https://openalex.org/W7160125476","https://openalex.org/W7166831857","https://openalex.org/W4416037326","https://openalex.org/W4412886779","https://openalex.org/W7131777382"],"abstract_inverted_index":{"Elena":[0],"Sofia":[1],"Ruzzetti,":[2],"Fabio":[3],"Massimo":[4],"Zanzotto,":[5],"Tommaso":[6],"Caselli.":[7],"Proceedings":[8],"of":[9,13,17],"the":[10,14,18],"19th":[11],"Conference":[12],"European":[15],"Chapter":[16],"Association":[19],"for":[20],"Computational":[21],"Linguistics":[22],"(Volume":[23],"1:":[24],"Long":[25],"Papers).":[26],"2026.":[27]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2026-03-24T00:00:00"}
