{"id":"https://openalex.org/W3213620104","doi":null,"title":"Think Big, Teach Small: Do Language Models Distil Occam\u2019s Razor?","display_name":"Think Big, Teach Small: Do Language Models Distil Occam\u2019s Razor?","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W3213620104","mag":"3213620104"},"language":"en","primary_location":{"id":"mag:3213620104","doi":null,"is_oa":false,"landing_page_url":"https://proceedings.neurips.cc/paper/2021/hash/0cd6a652ed1f7811192db1f700c8f0e7-Abstract.html","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081405293","display_name":"Gonzalo Jaimovitch-L\u00f3pez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gonzalo Jaimovitch-Lopez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062366340","display_name":"David Castellano Falc\u00f3n","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Castellano Falc\u00f3n","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050804466","display_name":"C\u00e8sar Ferri","orcid":"https://orcid.org/0000-0002-8975-1120","observed_orcids":["https://orcid.org/0000-0002-8975-1120"]},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"C\u00e8sar Ferri","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8975-1120","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029864546","display_name":"Jos\u00e9 Hern\u00e1ndez\u2010Orallo","orcid":"https://orcid.org/0000-0001-9746-7632","observed_orcids":["https://orcid.org/0000-0001-9746-7632"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Hern\u00e1ndez\u2010Orallo","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9746-7632","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0725,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33601833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"34","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4058000147342682,"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":0.4058000147342682,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1525000035762787,"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":0.07460000365972519,"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/language-models","display_name":"language models","score":0.8149999976158142},{"id":"https://openalex.org/keywords/occam-s-razor","display_name":"Occam's razor","score":0.9390000104904175},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.5299999713897705},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5180000066757202},{"id":"https://openalex.org/keywords/small-models","display_name":"small models","score":0.3930000066757202},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.3479999899864197},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C78469957","wikidata":"https://www.wikidata.org/wiki/Q838062","display_name":"occam","level":2,"score":0.9390316009521484},{"id":"https://openalex.org/C64802038","wikidata":"https://www.wikidata.org/wiki/Q131012","display_name":"Occam's razor","level":2,"score":0.8867180347442627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404469847679138},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6009122133255005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3558582067489624},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14163893461227417},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.11261218786239624}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3213620104","doi":null,"is_oa":false,"landing_page_url":"https://proceedings.neurips.cc/paper/2021/hash/0cd6a652ed1f7811192db1f700c8f0e7-Abstract.html","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"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/W7197029642","https://openalex.org/W7197045644","https://openalex.org/W7139581039","https://openalex.org/W7196961304","https://openalex.org/W7133235367","https://openalex.org/W7197052620","https://openalex.org/W7131779678","https://openalex.org/W7196981086","https://openalex.org/W7133212267","https://openalex.org/W7197010556"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-11-22T00:00:00"}
