{"id":"https://openalex.org/W7214699704","doi":"https://doi.org/10.48550/arxiv.2609.34864","title":"On the Limits of Metacognitive Monitoring in LLMs","display_name":"On the Limits of Metacognitive Monitoring in LLMs","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214699704","doi":"https://doi.org/10.48550/arxiv.2609.34864"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34864","pdf_url":"https://arxiv.org/pdf/2609.34864","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129531125","display_name":"Dongqi Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Dongqi","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139661762","display_name":"Yifan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Yifan","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153425709","display_name":"Dongsheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Dongsheng","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5576000213623047,"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":0.5576000213623047,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08420000225305557,"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":0.0803999975323677,"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/metacognitive-monitoring","display_name":"metacognitive monitoring","score":0.9940000176429749},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.7070000171661377},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9210000038146973},{"id":"https://openalex.org/keywords/self-review","display_name":"self-review","score":0.628000020980835},{"id":"https://openalex.org/keywords/cross-model-evaluation","display_name":"cross-model evaluation","score":0.640999972820282},{"id":"https://openalex.org/keywords/problem-solving","display_name":"problem solving","score":0.32199999690055847},{"id":"https://openalex.org/keywords/mathematical-problem-solving","display_name":"mathematical problem solving","score":0.5799999833106995},{"id":"https://openalex.org/keywords/question-difficulty","display_name":"question difficulty","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C118147538","wikidata":"https://www.wikidata.org/wiki/Q1126970","display_name":"Metacognition","level":3,"score":0.734000027179718},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5968000292778015},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.567300021648407},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45660001039505005},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C48444904","wikidata":"https://www.wikidata.org/wiki/Q4116378","display_name":"Self-confidence","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34864","pdf_url":"https://arxiv.org/pdf/2609.34864","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.34864","doi":"https://doi.org/10.48550/arxiv.2609.34864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34864","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34864","pdf_url":"https://arxiv.org/pdf/2609.34864","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214699704.pdf","grobid_xml":"https://content.openalex.org/works/W7214699704.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1598182466","https://openalex.org/W2000803197","https://openalex.org/W2001557538","https://openalex.org/W2005570340","https://openalex.org/W2090483808","https://openalex.org/W2145731452","https://openalex.org/W2146006411","https://openalex.org/W2626857346","https://openalex.org/W4285429195","https://openalex.org/W4321594373","https://openalex.org/W4383371132","https://openalex.org/W4389518686","https://openalex.org/W4389519449","https://openalex.org/W4399803256","https://openalex.org/W4402670032","https://openalex.org/W4402670356","https://openalex.org/W4402671952","https://openalex.org/W4404131920","https://openalex.org/W4404341075","https://openalex.org/W4406840771","https://openalex.org/W4412886690","https://openalex.org/W4412887967","https://openalex.org/W4415797148","https://openalex.org/W4415932859","https://openalex.org/W4416037117","https://openalex.org/W6929280941","https://openalex.org/W7160868193","https://openalex.org/W7166155130","https://openalex.org/W7213281345"],"related_works":["https://openalex.org/W7214701602","https://openalex.org/W7141242820","https://openalex.org/W7162470200","https://openalex.org/W4406603696","https://openalex.org/W7160904731","https://openalex.org/W7154999192","https://openalex.org/W7166802955","https://openalex.org/W7134814024","https://openalex.org/W7161239227","https://openalex.org/W6979268838"],"abstract_inverted_index":{"Reliable":[0],"decisions":[1],"depend":[2],"on":[3,86,99,109,114],"recognizing":[4],"when":[5],"an":[6],"answer":[7],"may":[8],"be":[9],"wrong.":[10],"In":[11],"biological":[12],"cognition,":[13],"metacognitive":[14],"monitoring":[15],"can":[16,51],"dissociate":[17],"from":[18,82],"task":[19,49],"performance,":[20],"raising":[21],"the":[22,38,127,135],"question":[23],"of":[24,41,61],"how":[25],"closely":[26],"solving":[27],"and":[28,131,144,153],"judging":[29],"are":[30],"linked":[31],"in":[32,157],"language":[33],"models.":[34],"Here":[35],"we":[36],"study":[37],"confidence":[39,68],"reports":[40],"four":[42],"frontier":[43],"models":[44,137,158],"across":[45],"15":[46],"benchmarks.":[47],"High":[48],"accuracy":[50],"coexist":[52],"with":[53,159],"weak":[54],"error":[55],"discrimination:":[56],"a":[57,90],"model":[58],"solves":[59],"97%":[60],"competition":[62],"mathematics":[63],"problems":[64],"while":[65,94],"its":[66],"answer-time":[67],"ranks":[69],"correct":[70,80,107],"answers":[71,81,108],"above":[72,112],"errors":[73,83,113,132,146],"barely":[74],"better":[75],"than":[76],"chance.":[77],"Confidence":[78],"separates":[79],"more":[84],"effectively":[85],"questions":[87,111,143],"solved":[88],"by":[89,134],"separate":[91],"reference":[92],"model,":[93],"review":[95],"brings":[96],"limited":[97],"improvement":[98],"reference-hard":[100],"questions.":[101],"Aggregate":[102],"discrimination":[103],"also":[104],"rewards":[105],"ranking":[106],"easy":[110],"hard":[115],"ones,":[116],"which":[117],"question-only":[118],"forecasts":[119],"already":[120],"do":[121],"well.":[122],"Cross-evaluation":[123],"helps":[124],"most":[125],"where":[126],"evaluator":[128],"answered":[129],"correctly,":[130],"shared":[133,145],"two":[136],"usually":[138],"retain":[139],"high":[140],"confidence.":[141],"Hard":[142],"remain":[147],"difficult":[148],"targets":[149],"for":[150],"prompted":[151],"self-review":[152],"peer":[154],"oversight,":[155],"even":[156],"strong":[160],"problem-solving":[161],"performance.":[162]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}