{"id":"https://openalex.org/W4416033751","doi":"https://doi.org/10.18653/v1/2025.starsem-1.28","title":"How Do Large Language Models Evaluate Lexical Complexity?","display_name":"How Do Large Language Models Evaluate Lexical Complexity?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033751","doi":"https://doi.org/10.18653/v1/2025.starsem-1.28"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.starsem-1.28","doi":"https://doi.org/10.18653/v1/2025.starsem-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.starsem-1.28","pdf_url":"https://aclanthology.org/2025.starsem-1.28.pdf","source":{"id":"https://openalex.org/S4306420406","display_name":"Joint Conference on Lexical and Computational Semantics","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 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.starsem-1.28.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094077421","display_name":"Abdelhak Kelious","orcid":"https://orcid.org/0009-0009-1912-2116","observed_orcids":["https://orcid.org/0009-0009-1912-2116"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121906","display_name":"Analyse et Traitement Informatique de la Langue Fran\u00e7aise","ror":"https://ror.org/02cy9g557","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210121906","https://openalex.org/I4210150854","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdelhak Kelious","raw_affiliation_strings":["University of Lorraine and CNRS / ATILF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lorraine and CNRS / ATILF","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121906","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114677066","display_name":"Mathieu Constant","orcid":"https://orcid.org/0000-0003-4851-9461","observed_orcids":["https://orcid.org/0000-0003-4851-9461","https://orcid.org/0000-0002-9910-594X"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121906","display_name":"Analyse et Traitement Informatique de la Langue Fran\u00e7aise","ror":"https://ror.org/02cy9g557","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210121906","https://openalex.org/I4210150854","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Constant","raw_affiliation_strings":["University of Lorraine and CNRS / ATILF"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lorraine and CNRS / ATILF","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121906","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026354993","display_name":"Christophe Coeur","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Coeur","raw_affiliation_strings":["Consultant"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consultant","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"348","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.513700008392334,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.513700008392334,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.22120000422000885,"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":0.1907999962568283,"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/lexical-complexity","display_name":"lexical complexity","score":0.9750000238418579},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.6380000114440918},{"id":"https://openalex.org/keywords/chain-of-thought-prompting","display_name":"chain-of-thought prompting","score":0.9449999928474426},{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.925000011920929},{"id":"https://openalex.org/keywords/one-shot-prompting","display_name":"one-shot prompting","score":0.9039999842643738},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.8569999933242798},{"id":"https://openalex.org/keywords/forecast-calibration","display_name":"forecast calibration","score":0.6320000290870667},{"id":"https://openalex.org/keywords/manual-annotation","display_name":"manual annotation","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6225000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5436000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.24699999392032623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.starsem-1.28","doi":"https://doi.org/10.18653/v1/2025.starsem-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.starsem-1.28","pdf_url":"https://aclanthology.org/2025.starsem-1.28.pdf","source":{"id":"https://openalex.org/S4306420406","display_name":"Joint Conference on Lexical and Computational Semantics","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 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.starsem-1.28","doi":"https://doi.org/10.18653/v1/2025.starsem-1.28","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.starsem-1.28","pdf_url":"https://aclanthology.org/2025.starsem-1.28.pdf","source":{"id":"https://openalex.org/S4306420406","display_name":"Joint Conference on Lexical and Computational Semantics","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 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033751.pdf","grobid_xml":"https://content.openalex.org/works/W4416033751.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4287160675","https://openalex.org/W4387561528","https://openalex.org/W4389157038","https://openalex.org/W4392822465","https://openalex.org/W4395474395","https://openalex.org/W4401306886","https://openalex.org/W4404782844","https://openalex.org/W4404783774","https://openalex.org/W4405655184","https://openalex.org/W4406461941","https://openalex.org/W4411272222"],"related_works":["https://openalex.org/W3184385795","https://openalex.org/W3186632741","https://openalex.org/W4403431717","https://openalex.org/W6903789644","https://openalex.org/W3185028162","https://openalex.org/W4399997476","https://openalex.org/W3185946373","https://openalex.org/W3152828337","https://openalex.org/W3185606300","https://openalex.org/W3171963800"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"explore":[4],"the":[5,15,24,35,38,41,47,96,99],"prediction":[6],"of":[7,17,26,37,98],"lexical":[8],"complexity":[9],"by":[10],"combining":[11],"supervised":[12,103],"approaches":[13],"and":[14,32,55,80],"use":[16],"large":[18],"language":[19],"models":[20],"(LLMs).We":[21],"first":[22],"evaluate":[23],"impact":[25],"different":[27],"prompting":[28],"strategies":[29],"(zero-shot,":[30],"oneshot,":[31],"chain-of-thought)":[33],"on":[34,84],"quality":[36],"predictions,":[39],"comparing":[40],"results":[42,51],"with":[43],"human":[44,66,81],"annotations":[45,100],"from":[46,60],"CompLex":[48],"2.0":[49],"corpus.Our":[50],"indicate":[52],"that":[53],"LLMs,":[54],"in":[56,101],"particular":[57],"gpt-4o,":[58],"benefit":[59],"explicit":[61],"instructions":[62],"to":[63,75,94],"better":[64,76],"approximate":[65],"judgments,":[67],"although":[68],"some":[69],"discrepancies":[70],"remain.Moreover,":[71],"a":[72,91,102],"calibration":[73],"approach":[74],"align":[77],"LLMs":[78],"predictions":[79],"judgements":[82],"based":[83],"few":[85],"manually":[86],"annotated":[87],"data":[88],"appears":[89],"as":[90],"promising":[92],"solution":[93],"improve":[95],"reliability":[97],"scenario.":[104]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-11-08T00:00:00"}