{"id":"https://openalex.org/W4400723242","doi":"https://doi.org/10.1016/j.neunet.2024.106550","title":"Arithmetic with language models: From memorization to computation","display_name":"Arithmetic with language models: From memorization to computation","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400723242","doi":"https://doi.org/10.1016/j.neunet.2024.106550","pmid":"https://pubmed.ncbi.nlm.nih.gov/39068682"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2024.106550","doi":"https://doi.org/10.1016/j.neunet.2024.106550","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2024.106550","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2024.106550","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027196976","display_name":"Davide Maltoni","orcid":"https://orcid.org/0000-0002-6329-6756","observed_orcids":["https://orcid.org/0000-0002-6329-6756"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Maltoni","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Bologna, Italy. Electronic address: davide.maltoni@unibo.it","Department of Computer Science and Engineering, University of Bologna, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bologna, Italy. Electronic address: davide.maltoni@unibo.it","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010414428","display_name":"Matteo Ferrara","orcid":"https://orcid.org/0000-0002-4020-1419","observed_orcids":["https://orcid.org/0000-0002-4020-1419"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Matteo Ferrara","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Bologna, Italy. Electronic address: matteo.ferrara@unibo.it","Department of Computer Science and Engineering, University of Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4020-1419","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bologna, Italy. Electronic address: matteo.ferrara@unibo.it","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010414428"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":1.0287,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76785253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"179","issue":null,"first_page":"106550","last_page":"106550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7792999744415283,"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":0.7792999744415283,"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":0.09000000357627869,"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/T10320","display_name":"Neural Networks and Applications","score":0.015200000256299973,"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/large-language-models","display_name":"large language models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/arithmetic-computation","display_name":"arithmetic computation","score":0.8980000019073486},{"id":"https://openalex.org/keywords/binary-addition","display_name":"binary addition","score":0.921999990940094},{"id":"https://openalex.org/keywords/binary-multiplication","display_name":"binary multiplication","score":0.9980000257492065},{"id":"https://openalex.org/keywords/extrapolation","display_name":"extrapolation","score":0.8920000195503235},{"id":"https://openalex.org/keywords/emergent-computation","display_name":"emergent computation","score":0.8360000252723694},{"id":"https://openalex.org/keywords/token-representation","display_name":"token representation","score":0.37400001287460327},{"id":"https://openalex.org/keywords/internal-representations","display_name":"internal representations","score":0.6100000143051147}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.7137590646743774},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.6847532987594604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607822775840759},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6308186054229736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221419095993042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40943917632102966},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35918962955474854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2967260777950287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2646090090274811},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.2210196852684021}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008433","descriptor_name":"Mathematics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008568","descriptor_name":"Memory","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1016/j.neunet.2024.106550","doi":"https://doi.org/10.1016/j.neunet.2024.106550","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2024.106550","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:39068682","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39068682","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2308.01154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.01154","pdf_url":"https://arxiv.org/pdf/2308.01154","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/975900","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/975900","pdf_url":"https://cris.unibo.it/bitstream/11585/975900/1/1-s2.0-S089360802400474X-main.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2308.01154","doi":"https://doi.org/10.48550/arxiv.2308.01154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.01154","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1016/j.neunet.2024.106550","doi":"https://doi.org/10.1016/j.neunet.2024.106550","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2024.106550","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2523060838","https://openalex.org/W2626778328","https://openalex.org/W2787214294","https://openalex.org/W2793350103","https://openalex.org/W2950645060","https://openalex.org/W2974596953","https://openalex.org/W3001279689","https://openalex.org/W3016682301","https://openalex.org/W3101673779","https://openalex.org/W3133029875","https://openalex.org/W3159900299","https://openalex.org/W3165051279","https://openalex.org/W3168829745","https://openalex.org/W3193068792","https://openalex.org/W4221143046","https://openalex.org/W4283026156","https://openalex.org/W4285127912","https://openalex.org/W4316135772","https://openalex.org/W4360836968","https://openalex.org/W4362679046","https://openalex.org/W4366835609","https://openalex.org/W4378508793","https://openalex.org/W4378976798","https://openalex.org/W4383860315","https://openalex.org/W4385812312","https://openalex.org/W4389519056"],"related_works":["https://openalex.org/W4402671225","https://openalex.org/W4404088822","https://openalex.org/W4403873935","https://openalex.org/W4389261274","https://openalex.org/W4403364982","https://openalex.org/W4404334616","https://openalex.org/W4416034597","https://openalex.org/W3215529831","https://openalex.org/W4415798039","https://openalex.org/W4416036356"],"abstract_inverted_index":{"A":[0],"better":[1],"understanding":[2],"of":[3,10,16,94],"the":[4,37,98,108,111,120,125,129],"emergent":[5],"computation":[6,121],"and":[7,23,50,66,90,101],"problem-solving":[8],"capabilities":[9,100],"recent":[11],"large":[12],"language":[13,32,84,112],"models":[14],"is":[15,133],"paramount":[17],"importance":[18],"to":[19,35,86,96,135],"further":[20],"improve":[21],"them":[22],"broaden":[24],"their":[25],"applicability.":[26],"This":[27],"work":[28],"investigates":[29],"how":[30],"a":[31,53,62,82,92],"model,":[33],"trained":[34,81],"predict":[36],"next":[38],"token,":[39],"can":[40],"perform":[41],"arithmetic":[42],"computations":[43],"generalizing":[44],"beyond":[45],"training":[46],"data.":[47,78],"Binary":[48],"addition":[49],"multiplication":[51],"constitute":[52],"good":[54],"testbed":[55],"for":[56,76],"this":[57],"purpose,":[58],"since":[59],"they":[60],"require":[61],"very":[63],"small":[64],"vocabulary":[65],"exhibit":[67],"relevant":[68],"input/output":[69],"discontinuities":[70],"making":[71],"smooth":[72],"input":[73,130],"interpolation":[74],"ineffective":[75],"novel":[77],"We":[79],"successfully":[80],"light":[83],"model":[85,113],"learn":[87],"these":[88],"tasks":[89],"ran":[91],"number":[93],"experiments":[95],"investigate":[97],"extrapolation":[99],"internal":[102,138],"information":[103],"processing.":[104],"Our":[105],"findings":[106],"support":[107],"hypothesis":[109],"that":[110],"works":[114],"as":[115],"an":[116,136],"Encoding-Regression-Decoding":[117],"machine":[118],"where":[119],"takes":[122],"place":[123],"in":[124],"value":[126],"space":[127],"once":[128],"token":[131],"representation":[132],"mapped":[134],"appropriate":[137],"representation.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-07-18T00:00:00"}
