{"id":"https://openalex.org/W4406892603","doi":"https://doi.org/10.1109/fllm63129.2024.10852449","title":"Comparative Analysis of Reasoning Capabilities in Foundation Models","display_name":"Comparative Analysis of Reasoning Capabilities in Foundation Models","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892603","doi":"https://doi.org/10.1109/fllm63129.2024.10852449"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5045362954","display_name":"J. de Curt\u00f2","orcid":null},"institutions":[{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]},{"id":"https://openalex.org/I96580804","display_name":"Comillas Pontifical University","ror":"https://ror.org/017mdc710","country_code":"ES","type":"education","lineage":["https://openalex.org/I96580804"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"J. de Curt\u00f2","raw_affiliation_strings":["Universitat Oberta de Catalunya Universidad Pontificia Comillas,BARCELONA Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Oberta de Catalunya Universidad Pontificia Comillas,BARCELONA Supercomputing Center","institution_ids":["https://openalex.org/I138847295","https://openalex.org/I96580804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066504412","display_name":"I. de Zarz\u00e0","orcid":"https://orcid.org/0000-0002-5844-7871"},"institutions":[{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"I. de Zarz\u00e0","raw_affiliation_strings":["Universitat Oberta de Catalunya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Oberta de Catalunya","institution_ids":["https://openalex.org/I138847295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045362954"],"corresponding_institution_ids":["https://openalex.org/I138847295","https://openalex.org/I96580804"],"apc_list":null,"apc_paid":null,"fwci":1.627,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87041115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.5888000130653381,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.5888000130653381,"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/foundation","display_name":"Foundation (evidence)","score":0.6960351467132568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6382572650909424},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.32089653611183167},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13746434450149536},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07584011554718018}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6960351467132568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6382572650909424},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.32089653611183167},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13746434450149536},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07584011554718018},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,35,39,72,131,182],"large":[4],"language":[5,15],"models":[6,59,121,168],"(LLMs)":[7],"has":[8],"led":[9],"to":[10,56],"significant":[11,100],"improvements":[12],"in":[13,102,123,137,145,184,200],"natural":[14],"processing":[16],"tasks,":[17,187],"yet":[18],"their":[19],"capability":[20],"for":[21,177,191],"complex":[22,153,185],"reasoning":[23,37,96,147,161,198],"across":[24,60,116,194],"diverse":[25],"domains":[26,195],"remains":[27],"understudied.":[28],"This":[29,172],"paper":[30],"presents":[31],"a":[32,53,84],"comprehensive":[33,85],"evaluation":[34],"the":[36,77,90,152,164,178,189],"abilities":[38],"six":[40],"state-of-the-art":[41],"LLMs:":[42],"Mixtral-8x7B,":[43],"Phi-3,":[44],"LLaMA":[45],"3.1-8B,":[46],"Gemma-2-9b,":[47],"Mistral-7B,":[48],"and":[49,68,94,106,160,180,196],"OLMo-7B.":[50],"We":[51],"employ":[52],"novel":[54],"framework":[55],"assess":[57],"these":[58],"eight":[61],"academic":[62],"domains,":[63],"including":[64],"Physics,":[65],"Mathematics,":[66],"Chemistry,":[67],"Economics,":[69],"with":[70,104,127,140],"problems":[71],"varying":[73],"difficulty":[74],"levels.":[75],"Leveraging":[76],"MareNostrum":[78],"5":[79],"supercomputer,":[80],"our":[81],"study":[82,173],"provides":[83],"evaluation,":[86],"offering":[87],"insights":[88,176],"into":[89],"models\u2019":[91],"performance,":[92,103],"consistency,":[93],"step-by-step":[95],"capabilities.":[97],"Results":[98],"reveal":[99],"variations":[101],"Mixtral-8x7B":[105],"Phi-3":[107],"demonstrating":[108],"superior":[109],"overall":[110],"capabilities,":[111],"while":[112],"domain-specific":[113],"strengths":[114],"emerged":[115],"different":[117],"models.":[118],"Notably,":[119],"all":[120],"excelled":[122],"Economics":[124],"but":[125],"struggled":[126],"Optimization":[128],"problems.":[129],"Analysis":[130],"step":[132],"accuracy":[133],"highlighted":[134],"intriguing":[135],"differences":[136],"problem-solving":[138,186],"approaches,":[139],"Gemma-2-9b":[141],"showing":[142],"exceptional":[143],"transparency":[144],"its":[146],"process.":[148],"Our":[149],"findings":[150],"highlight":[151],"relationship":[154],"between":[155],"model":[156],"architecture,":[157],"training":[158],"methodologies,":[159],"abilities,":[162],"challenging":[163],"notion":[165],"that":[166],"larger":[167],"invariably":[169],"perform":[170],"better.":[171],"contributes":[174],"valuable":[175],"development":[179],"application":[181],"AI":[183],"emphasizing":[188],"need":[190],"balanced":[192],"capabilities":[193],"transparent":[197],"processes":[199],"future":[201],"LLM":[202],"development.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}