{"id":"https://openalex.org/W4415311404","doi":"https://doi.org/10.48550/arxiv.2506.14046","title":"Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications","display_name":"Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4415311404","doi":"https://doi.org/10.48550/arxiv.2506.14046"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.14046","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14046","pdf_url":"https://arxiv.org/pdf/2506.14046","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":null,"license_id":null,"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/2506.14046","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110847185","display_name":"David Kogan","orcid":"https://orcid.org/0009-0004-9520-8775","observed_orcids":["https://orcid.org/0009-0004-9520-8775"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kogan, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057293051","display_name":"Max Schumacher","orcid":"https://orcid.org/0000-0003-0486-3498","observed_orcids":["https://orcid.org/0000-0003-0486-3498"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schumacher, Max","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075408736","display_name":"Sam Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Sam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104339505","display_name":"Masanori Suzuki","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzuki, Masanori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Smith, Melissa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smith, Melissa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119613018","display_name":"Chloe Bellows","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bellows, Chloe Sophia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113028758","display_name":"Jared Bernstein","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernstein, Jared","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":null,"has_fulltext":false,"cited_by_count":1,"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/T13629","display_name":"Text Readability and Simplification","score":0.9922000169754028,"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/T13629","display_name":"Text Readability and Simplification","score":0.9922000169754028,"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":0.005100000184029341,"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":0.0015999999595806003,"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/conversational-text","display_name":"conversational text","score":0.9049999713897705},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.5460000038146973},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.703000009059906},{"id":"https://openalex.org/keywords/expert-annotation","display_name":"expert annotation","score":0.6000000238418579},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.31200000643730164},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595000267028809},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6801999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121000051498413},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3393000066280365},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2992770021","wikidata":"https://www.wikidata.org/wiki/Q7247850","display_name":"Production model","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.14046","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14046","pdf_url":"https://arxiv.org/pdf/2506.14046","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.14046","doi":"https://doi.org/10.48550/arxiv.2506.14046","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14046","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.14046","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14046","pdf_url":"https://arxiv.org/pdf/2506.14046","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214740036","https://openalex.org/W7140135233","https://openalex.org/W7160154359","https://openalex.org/W7166563651","https://openalex.org/W4417529114","https://openalex.org/W7162679820","https://openalex.org/W7160237926","https://openalex.org/W7130533524","https://openalex.org/W7222392576","https://openalex.org/W7131209346"],"abstract_inverted_index":{"There":[0],"is":[1],"an":[2],"unmet":[3],"need":[4],"to":[5,75,84],"evaluate":[6],"the":[7,81,85],"language":[8],"difficulty":[9,65],"of":[10,14,30,40],"short,":[11],"conversational":[12,32],"passages":[13,34],"text,":[15],"particularly":[16],"for":[17,87],"training":[18],"and":[19,53,71,89],"filtering":[20],"Large":[21],"Language":[22],"Models":[23],"(LLMs).":[24],"We":[25,43,55],"introduce":[26],"Ace-CEFR,":[27,49],"a":[28],"dataset":[29,83],"English":[31],"text":[33,41,64],"expert-annotated":[35],"with":[36,45],"their":[37],"corresponding":[38],"level":[39],"difficulty.":[42],"experiment":[44],"several":[46],"models":[47,52,58],"on":[48,60],"including":[50],"Transformer-based":[51],"LLMs.":[54],"show":[56],"that":[57],"trained":[59],"Ace-CEFR":[61,82],"can":[62],"measure":[63],"more":[66],"accurately":[67],"than":[68],"human":[69],"experts":[70],"have":[72],"latency":[73],"appropriate":[74],"production":[76],"environments.":[77],"Finally,":[78],"we":[79],"release":[80],"public":[86],"research":[88],"development.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2025-10-18T00:00:00"}