{"id":"https://openalex.org/W7214929031","doi":"https://doi.org/10.48550/arxiv.2609.38005","title":"Diagnosing and Improving Probabilistic Reasoning in Large Language Models","display_name":"Diagnosing and Improving Probabilistic Reasoning in Large Language Models","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214929031","doi":"https://doi.org/10.48550/arxiv.2609.38005"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38005","pdf_url":"https://arxiv.org/pdf/2609.38005","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/2609.38005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106416044","display_name":"Huaman Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Huaman","raw_affiliation_strings":["Department of Computer Science Northwestern University Evanston , IL 60201 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Northwestern University Evanston , IL 60201 , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153659147","display_name":"Dingcheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Dingcheng","raw_affiliation_strings":["Department of Computer Science Northwestern University Evanston , IL 60201 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Northwestern University Evanston , IL 60201 , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089749790","display_name":"Jason D. Hartline","orcid":"https://orcid.org/0000-0001-5505-6819","observed_orcids":["https://orcid.org/0000-0001-5505-6819"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hartline, Jason","raw_affiliation_strings":["Department of Computer Science Northwestern University Evanston , IL 60201 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Northwestern University Evanston , IL 60201 , USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132895071","display_name":"Jessica Hullman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hullman, Jessica","raw_affiliation_strings":["Department of Computer Science Northwestern University Evanston , IL 60201 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Northwestern University Evanston , IL 60201 , USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"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/T10181","display_name":"Natural Language Processing Techniques","score":0.24300000071525574,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.24300000071525574,"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/T10028","display_name":"Topic Modeling","score":0.2287999987602234,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.08839999884366989,"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/probabilistic-reasoning","display_name":"probabilistic reasoning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.996999979019165},{"id":"https://openalex.org/keywords/belief-formation","display_name":"belief formation","score":0.921999990940094},{"id":"https://openalex.org/keywords/utility-maximization","display_name":"utility maximization","score":0.5519999861717224},{"id":"https://openalex.org/keywords/synthetic-benchmark","display_name":"synthetic benchmark","score":0.6990000009536743}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.8087000250816345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6365000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6148999929428101},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.3199000060558319},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38005","pdf_url":"https://arxiv.org/pdf/2609.38005","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.2609.38005","doi":"https://doi.org/10.48550/arxiv.2609.38005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38005","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38005","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38005","pdf_url":"https://arxiv.org/pdf/2609.38005","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":[{"id":"https://openalex.org/G1453181110","display_name":null,"funder_award_id":"#2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3562386289","display_name":null,"funder_award_id":"#2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4676224565","display_name":"ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI)","funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5367127336","display_name":null,"funder_award_id":"#2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214929031.pdf","grobid_xml":"https://content.openalex.org/works/W7214929031.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4285429195","https://openalex.org/W4389518686","https://openalex.org/W4416361850","https://openalex.org/W7128361140","https://openalex.org/W7212036357"],"related_works":["https://openalex.org/W6967168462","https://openalex.org/W7128361140","https://openalex.org/W7118304105","https://openalex.org/W4415090957","https://openalex.org/W4395021958","https://openalex.org/W4413423596","https://openalex.org/W7221775329","https://openalex.org/W4413819735","https://openalex.org/W4409348124","https://openalex.org/W7163886155"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"proposed":[6],"as":[7],"decision":[8,19,29,100,119],"assistants":[9],"who":[10],"must":[11],"reason":[12],"probabilistically":[13],"from":[14,37],"available":[15],"evidence":[16,39],"under":[17],"explicit":[18],"costs.":[20],"We":[21,73,109],"propose":[22],"a":[23,48,53],"decision-theoretic":[24],"framework":[25],"that":[26,46,111,130],"decomposes":[27],"LLMs'":[28],"loss":[30],"into":[31,44],"two":[32],"components:":[33],"forming":[34],"accurate":[35],"beliefs":[36,43],"provided":[38,49],"and":[40,70,95,98,129,135,146],"translating":[41],"those":[42],"actions":[45],"optimize":[47],"utility":[50],"function.":[51],"Using":[52],"synthetic":[54],"benchmark":[55],"with":[56],"known":[57],"ground":[58],"truth,":[59],"we":[60],"apply":[61],"the":[62,122],"decomposition":[63],"to":[64,127],"characterize":[65],"probabilistic":[66,116],"reasoning":[67,117],"in":[68,106],"frontier":[69],"open-sourced":[71],"models.":[72],"further":[74],"evaluate":[75],"whether":[76,90,99],"RL":[77],"interventions":[78],"targeting":[79,112,132],"beliefs,":[80],"decisions,":[81],"or":[82],"both":[83,138],"improve":[84,103],"these":[85],"components":[86,94],"across":[87,93],"three":[88],"domains,":[89],"improvements":[91],"transfer":[92],"elicitation":[96],"formats,":[97],"performance":[101],"can":[102],"without":[104,124],"improvement":[105],"belief":[107,133],"formation.":[108],"find":[110],"one":[113],"component":[114],"of":[115],"redistributes":[118],"loss,":[120],"improving":[121],"target":[123],"necessarily":[125],"transferring":[126],"others,":[128],"jointly":[131],"formation":[134],"decision-making":[136],"improves":[137],"but":[139],"hinges":[140],"on":[141],"matched":[142],"formats":[143],"between":[144],"training":[145],"evaluation.":[147]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-01T00:00:00"}