{"id":"https://openalex.org/W4415428125","doi":"https://doi.org/10.3233/faia251331","title":"ALF: A Fine-Grained French Analogical Dataset for Evaluating Lexical Knowledge of Large Language Models","display_name":"ALF: A Fine-Grained French Analogical Dataset for Evaluating Lexical Knowledge of Large Language Models","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428125","doi":"https://doi.org/10.3233/faia251331"},"language":null,"primary_location":{"id":"doi:10.3233/faia251331","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251331","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251331","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025327703","display_name":"Alexander Petrov","orcid":"https://orcid.org/0000-0003-4820-5227"},"institutions":[{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alexander Petrov","raw_affiliation_strings":["RALI, D\u00e9partement d\u2019informatique et de recherche op\u00e9rationelle, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"RALI, D\u00e9partement d\u2019informatique et de recherche op\u00e9rationelle, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210161954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041618066","display_name":"Antoine Venant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114212","display_name":"Laboratoire de Linguistique Formelle","ror":"https://ror.org/0223bz716","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210114212","https://openalex.org/I4210150854"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Venant","raw_affiliation_strings":["OLST, D\u00e9partement de linguistique et de traduction, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"OLST, D\u00e9partement de linguistique et de traduction, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210114212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033407539","display_name":"Fran\u00e7ois Lareau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114212","display_name":"Laboratoire de Linguistique Formelle","ror":"https://ror.org/0223bz716","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210114212","https://openalex.org/I4210150854"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Lareau","raw_affiliation_strings":["OLST, D\u00e9partement de linguistique et de traduction, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"OLST, D\u00e9partement de linguistique et de traduction, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210114212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023073062","display_name":"Yves Lepage","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yves Lepage","raw_affiliation_strings":["EBMT/NLP, Faculty of Science and Engineering, Waseda University"],"affiliations":[{"raw_affiliation_string":"EBMT/NLP, Faculty of Science and Engineering, Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034154991","display_name":"Philippe Langlais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Philippe Langlais","raw_affiliation_strings":["RALI, D\u00e9partement d\u2019informatique et de recherche op\u00e9rationelle, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"RALI, D\u00e9partement d\u2019informatique et de recherche op\u00e9rationelle, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210161954"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025327703"],"corresponding_institution_ids":["https://openalex.org/I4210161954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50462732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9866999983787537,"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/T13629","display_name":"Text Readability and Simplification","score":0.9811000227928162,"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/fluency","display_name":"Fluency","score":0.7505999803543091},{"id":"https://openalex.org/keywords/lexical-item","display_name":"Lexical item","score":0.511900007724762},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.4043000042438507},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33320000767707825},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.3314000070095062},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7505999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330000162124634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5407999753952026},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2777532361","wikidata":"https://www.wikidata.org/wiki/Q687185","display_name":"Lexicalization","level":2,"score":0.28790000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251331","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251331","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251331","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251331","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"undeniable":[1],"revolution":[2],"brought":[3],"forth":[4],"by":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"stems":[10],"from":[11,100],"the":[12,16,69,82,108,141],"amazing":[13],"fluency":[14,27],"of":[15,85,152],"texts":[17],"they":[18],"generate,":[19],"mastering":[20],"language":[21],"with":[22,60,78,128],"seemingly":[23],"human-like":[24],"finesse.":[25],"This":[26],"raises":[28],"a":[29,54,124],"key":[30],"scientific":[31],"question:":[32],"How":[33],"much":[34],"lexical":[35,76,83],"knowledge":[36],"do":[37],"LLMs":[38],"actually":[39],"capture":[40],"in":[41,65,144],"order":[42],"to":[43,115],"produce":[44],"such":[45],"fluent":[46],"language?":[47],"To":[48],"address":[49],"this,":[50],"we":[51,80],"present":[52],"ALF,":[53],"freely":[55],"available,":[56],"analogical":[57],"dataset":[58],"endowed":[59],"rich":[61],"lexicographic":[62],"information":[63],"grounded":[64],"Meaning-Text":[66],"Theory":[67],"for":[68,102,107,118],"French":[70],"language.":[71],"It":[72],"comprises":[73],"2600":[74],"fine-grained":[75],"analogies":[77,153],"which":[79],"evaluate":[81],"ability":[84],"five":[86],"off-the-shelf":[87],"LLMs,":[88],"namely":[89],"ChatGPT-4o":[90],"mini,":[91],"Llama3.0-8B,":[92],"Llama3.1-8B,":[93],"Qwen2.5-14B,":[94,119],"and":[95,110,113,134,154],"Mistral7B.":[96],"Their":[97],"performance":[98,159],"spans":[99],"45%":[101],"Mistral,":[103],"through":[104],"about":[105],"55%":[106],"ChatGPT":[109],"Llama":[111],"models,":[112],"up":[114],"nearly":[116],"60%":[117],"thus":[120],"qualifying":[121],"ALF":[122],"as":[123],"challenging":[125],"dataset.":[126],"Experimenting":[127],"larger":[129],"models":[130],"(OpenAI":[131],"o1,":[132],"Llama3.0/3.1-70B,":[133],"Qwen2.5-32B)":[135],"yields":[136],"rather":[137],"limited":[138],"returns":[139],"considering":[140],"drastic":[142],"increase":[143],"computational":[145],"cost.":[146],"We":[147],"further":[148],"identify":[149],"certain":[150],"types":[151],"prompting":[155],"methods":[156],"that":[157],"reveal":[158],"disparities.":[160]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}