{"id":"https://openalex.org/W7128639963","doi":"https://doi.org/10.5281/zenodo.18610844","title":"Multiple Choice Questions: Reasoning Makes Large Language Models More Self- Confident, Especially When They Are Wrong","display_name":"Multiple Choice Questions: Reasoning Makes Large Language Models More Self- Confident, Especially When They Are Wrong","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128639963","doi":"https://doi.org/10.5281/zenodo.18610844"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.18610844","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18610844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18610844","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115706883","display_name":"Tairan Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fu, Tairan","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":"https://orcid.org/0009-0009-9571-7250","affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125669153","display_name":"Javier Conde D\u00edaz","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Conde D\u00edaz, Javier","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"raw_orcid":"https://orcid.org/0000-0002-5304-0626","affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125642222","display_name":"GONZALO MARTINEZ","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"MARTINEZ, GONZALO","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"raw_orcid":"https://orcid.org/0000-0002-9125-6225","affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121988868","display_name":"Mar\u00eda Grandury","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Grandury, Mar\u00eda","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"raw_orcid":"https://orcid.org/0009-0009-4703-3348","affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125627191","display_name":"Pedro Reviriego","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Reviriego, Pedro","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid"],"raw_orcid":"https://orcid.org/0000-0003-2540-5234","affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8317999839782715},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6092000007629395},{"id":"https://openalex.org/keywords/multiple-choice","display_name":"Multiple choice","score":0.5618000030517578},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.36559998989105225},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2989000082015991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2987000048160553}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8317999839782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555000185966492},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C176730311","wikidata":"https://www.wikidata.org/wiki/Q867668","display_name":"Multiple choice","level":3,"score":0.5618000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4309000074863434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.18610844","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18610844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18610844","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18610844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"repo":[1],"provides":[2],"the":[3,8,35,50,59,76,80,83,86,95,106,109],"data":[4,107],"and":[5,56,79,91,104],"scripts":[6],"for":[7,71,75,82,102],"paper:":[9],"Multiple":[10],"Choice":[11],"Questions:":[12],"Thinking":[13],"Makes":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"More":[19],"Self-Confident":[20],"Even":[21],"When":[22],"They":[23],"are":[24],"Wrong,":[25],"IEEE":[26],"Intelligent":[27],"Systems":[28],"(in":[29],"press)":[30],"Repository":[31],"Contents":[32],"MMLU:":[33],"Contains":[34],"MMLU":[36],"datasets":[37],"from":[38,94],"https://huggingface.co/datasets/cais/mmlu":[39],"Results:":[40],"Include":[41],"results":[42],"under":[43],"two":[44,68],"types":[45],"of":[46,85],"prompts:":[47],"one":[48,74],"where":[49,58],"LLM":[51],"directly":[52],"generates":[53],"an":[54],"answer":[55,60],"another":[57],"is":[61],"generated":[62],"after":[63],"thinking.":[64],"Each":[65],"prompt":[66],"contains":[67],"CSV":[69],"files":[70],"each":[72],"dataset,":[73],"original":[77],"response":[78,87],"other":[81],"probabilities":[84],"options.":[88],"Figure:":[89],"Outputs":[90],"visualizations":[92],"derived":[93],"analysis.":[96],"Code:":[97],"The":[98],"Python":[99],"script":[100],"used":[101],"analyzing":[103],"plotting":[105],"in":[108],"Results":[110],"folder.":[111]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-12T00:00:00"}
