{"id":"https://openalex.org/W6930625373","doi":"https://doi.org/10.5281/zenodo.15007563","title":"XL-WSD-LLM: Extending XL-WSD to evaluate Large Language Models","display_name":"XL-WSD-LLM: Extending XL-WSD to evaluate Large Language Models","publication_year":2025,"publication_date":"2025-03-11","ids":{"openalex":"https://openalex.org/W6930625373","doi":"https://doi.org/10.5281/zenodo.15007563"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15007563","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15007563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15007563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Basile, Pierpaolo","orcid":"https://orcid.org/0000-0002-0545-1105"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Basile, Pierpaolo","raw_affiliation_strings":["University of Bari Aldo Moro"],"raw_orcid":"https://orcid.org/0000-0002-0545-1105","affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siciliani, Lucia","orcid":"https://orcid.org/0000-0002-1438-280X"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Siciliani, Lucia","raw_affiliation_strings":["University of Bari Aldo Moro"],"raw_orcid":"https://orcid.org/0000-0002-1438-280X","affiliations":[{"raw_affiliation_string":"University of Bari Aldo Moro","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":null,"display_name":"Musacchio, Elio","orcid":"https://orcid.org/0009-0006-9670-9998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Musacchio, Elio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-9670-9998","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"primary_topic":{"id":"https://openalex.org/T10528","display_name":"Adipokines, Inflammation, and Metabolic Diseases","score":0.049400001764297485,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10528","display_name":"Adipokines, Inflammation, and Metabolic Diseases","score":0.049400001764297485,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T10371","display_name":"Immune Response and Inflammation","score":0.033900000154972076,"subfield":{"id":"https://openalex.org/subfields/2403","display_name":"Immunology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10200","display_name":"Rheumatoid Arthritis Research and Therapies","score":0.024900000542402267,"subfield":{"id":"https://openalex.org/subfields/2745","display_name":"Rheumatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7854999899864197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7091000080108643},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6062999963760376},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5472999811172485},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.544700026512146},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48159998655319214},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4668999910354614},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46309998631477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7854999899864197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7091000080108643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6729999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6327999830245972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5472999811172485},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15007563","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15007563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15007563","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15007563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"score":0.44934722781181335,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"benchmark":[1,46],"extends":[2],"XL-WSD.":[3],"Starting":[4],"from":[5],"XL-WSD,":[6],"we":[7,37,75],"build":[8],"a":[9,25,32],"set":[10],"of":[11,41,48,71,118],"prompts":[12],"for":[13,59],"evaluating":[14],"Large":[15,119],"Language":[16,120],"Models":[17],"(LLMs)":[18],"in":[19,35,108],"two":[20,83],"settings.":[21],"The":[22,45],"first":[23],"is":[24,31,66],"multiple-choice":[26],"task,":[27],"and":[28,56,62,86],"the":[29,39,42,69,109,113],"second":[30],"generative":[33],"task":[34,61],"which":[36],"assess":[38],"quality":[40],"generated":[43],"definition.":[44],"consists":[47],"three":[49],"compressed":[50],"archives.":[51],"Two":[52],"archives":[53],"contain":[54],"training":[55],"test":[57],"data":[58,80,90,97],"each":[60],"language,":[63],"while":[64,94],"another":[65],"dedicated":[67],"to":[68],"output":[70],"several":[72],"LLMs":[73],"that":[74],"evaluate.":[76],"Each":[77],"dataset":[78],"includes":[79],"split":[81],"into":[82],"folders:":[84],"FT":[85,88],"TT.":[87],"contains":[89,96],"without":[91],"machine":[92],"translation,":[93],"TT":[95],"where":[98],"missing":[99],"glosses":[100],"are":[101,106],"automatically":[102],"translated.":[103],"More":[104],"details":[105],"available":[107],"pre-print":[110],"article":[111],"\"Exploring":[112],"Word":[114],"Sense":[115],"Disambiguation":[116],"Capabilities":[117],"Models,\"":[121],"published":[122],"on":[123],"arXiv.org.":[124]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}