{"id":"https://openalex.org/W4414474044","doi":"https://doi.org/10.1177/17248035251363882","title":"Evaluating Inductive Reasoning and Programming Capabilities of Large Language Models With The One-Dimensional Abstract Reasoning Corpus","display_name":"Evaluating Inductive Reasoning and Programming Capabilities of Large Language Models With The One-Dimensional Abstract Reasoning Corpus","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414474044","doi":"https://doi.org/10.1177/17248035251363882"},"language":"en","primary_location":{"id":"doi:10.1177/17248035251363882","is_oa":true,"landing_page_url":"https://doi.org/10.1177/17248035251363882","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/17248035251363882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082068867","display_name":"C\u00e9dric Mesnage","orcid":"https://orcid.org/0000-0002-2004-6378"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"C\u00e9dric Mesnage","raw_affiliation_strings":["Institute for Data Science and Artificial Intelligence, University of Exeter, UK"],"raw_orcid":"https://orcid.org/0000-0002-2004-6378","affiliations":[{"raw_affiliation_string":"Institute for Data Science and Artificial Intelligence, University of Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101835856","display_name":"Xiaoyang Wang","orcid":"https://orcid.org/0000-0001-9332-2700"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoyang Wang","raw_affiliation_strings":["Department of Computer Science, University of Exeter, UK"],"raw_orcid":"https://orcid.org/0000-0001-9332-2700","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035163413","display_name":"Hang Dong","orcid":"https://orcid.org/0000-0001-6828-6891"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hang Dong","raw_affiliation_strings":["Department of Computer Science, University of Exeter, UK"],"raw_orcid":"https://orcid.org/0000-0001-6828-6891","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056530008","display_name":"N.A. Aishwaryaprajna","orcid":null},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aishwaryaprajna","raw_affiliation_strings":["Department of Computer Science, University of Exeter, UK"],"raw_orcid":"https://orcid.org/0000-0003-4386-9745","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, UK","institution_ids":["https://openalex.org/I23923803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082068867"],"corresponding_institution_ids":["https://openalex.org/I23923803"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13092675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"2","first_page":"102","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9979000091552734,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.970300018787384,"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/inductive-reasoning","display_name":"Inductive reasoning","score":0.7626000046730042},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6344000101089478},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.5921000242233276},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.5378999710083008},{"id":"https://openalex.org/keywords/inductive-logic-programming","display_name":"Inductive logic programming","score":0.5038999915122986},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.5026000142097473},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.46560001373291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674000263214111},{"id":"https://openalex.org/C21563000","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive reasoning","level":2,"score":0.7626000046730042},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6344000101089478},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.5921000242233276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5848000049591064},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5263000130653381},{"id":"https://openalex.org/C2779382394","wikidata":"https://www.wikidata.org/wiki/Q1464197","display_name":"Inductive logic programming","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45350000262260437},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.42289999127388},{"id":"https://openalex.org/C2993131915","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive method","level":3,"score":0.4072999954223633},{"id":"https://openalex.org/C2986567400","wikidata":"https://www.wikidata.org/wiki/Q15777","display_name":"C programming language","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C50033165","wikidata":"https://www.wikidata.org/wiki/Q15712089","display_name":"Inductive programming","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.27379998564720154}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/17248035251363882","is_oa":true,"landing_page_url":"https://doi.org/10.1177/17248035251363882","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/29844680","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Journal contribution"}],"best_oa_location":{"id":"doi:10.1177/17248035251363882","is_oa":true,"landing_page_url":"https://doi.org/10.1177/17248035251363882","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2990138404","https://openalex.org/W4221143046","https://openalex.org/W4281557260","https://openalex.org/W4292779060","https://openalex.org/W4312592882","https://openalex.org/W4313384047","https://openalex.org/W4378508644","https://openalex.org/W4385572162","https://openalex.org/W4385652328","https://openalex.org/W4389518737","https://openalex.org/W4391494845","https://openalex.org/W4402671807","https://openalex.org/W4410126491"],"related_works":[],"abstract_inverted_index":{"We":[0,15,47,63,96,118],"present":[1],"an":[2,67,79],"initial":[3],"automated":[4],"test":[5],"to":[6,10,22,35,122],"evaluate":[7],"LLMs\u2019":[8],"capacity":[9],"perform":[11],"inductive":[12,33,116,135],"reasoning":[13,34,132],"tasks.":[14],"use":[16],"the":[17,39,92,98,102,106,112],"GPT-3.5":[18],"and":[19,60,66,72,109,129],"GPT-4":[20],"models":[21],"create":[23],"a":[24],"system":[25],"which":[26],"generates":[27],"Python":[28],"code":[29,114],"as":[30],"hypotheses":[31],"for":[32,115],"transform":[36],"sequences":[37],"of":[38,57,69,101,111],"One":[40],"Dimensional":[41],"Abstract":[42],"Reasoning":[43],"Corpus":[44],"(1D-ARC)":[45],"challenge.":[46],"experiment":[48],"with":[49,84,133],"three":[50],"prompting":[51,87,94],"techniques,":[52],"namely":[53],"standard":[54,93],"prompting,":[55],"Chain":[56],"Thought":[58],"(CoT),":[59],"direct":[61],"feedback.":[62],"provide":[64],"results":[65],"analysis":[68],"cost-to-success":[70],"rate":[71,83,108],"benefit-cost":[73],"ratio.":[74],"Our":[75],"best":[76],"result":[77],"is":[78],"overall":[80],"25%":[81],"success":[82],"our":[85,124],"CoT":[86],"on":[88],"GPT-4,":[89],"significantly":[90],"surpassing":[91],"approach.":[95],"assess":[97],"programming":[99],"capabilities":[100],"LLM":[103],"by":[104],"analysing":[105],"execution":[107],"errors":[110],"generated":[113],"reasoning.":[117,136],"discuss":[119],"potential":[120],"avenues":[121],"improve":[123],"experiments,":[125],"testing":[126],"other":[127],"strategies,":[128],"combining":[130],"deductive":[131],"LLM-based":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}