{"id":"https://openalex.org/W7166705739","doi":"https://doi.org/10.48550/arxiv.2606.29182","title":"Evidence-Informed LLM Beliefs for Continual Scientific Discovery","display_name":"Evidence-Informed LLM Beliefs for Continual Scientific Discovery","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166705739","doi":"https://doi.org/10.48550/arxiv.2606.29182"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139651097","display_name":"Dhruv Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Dhruv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120695081","display_name":"Reece Adamson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adamson, Reece","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139670619","display_name":"Andrew McCallum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McCallum, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139644852","display_name":"Peter Clark","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clark, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077726785","display_name":"Ashish Sabharwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabharwal, Ashish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139652581","display_name":"Bodhisattwa Prasad Majumder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Majumder, Bodhisattwa Prasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14669999480247498,"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":0.14669999480247498,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.11890000104904175,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06679999828338623,"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/spurious-relationship","display_name":"Spurious relationship","score":0.6425999999046326},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.6366000175476074},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4697999954223633},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4154999852180481},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/confirmation-bias","display_name":"Confirmation bias","score":0.32820001244544983},{"id":"https://openalex.org/keywords/falsifiability","display_name":"Falsifiability","score":0.30660000443458557}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5331000089645386},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4154999852180481},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3066999912261963},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C124056412","wikidata":"https://www.wikidata.org/wiki/Q3320364","display_name":"Scientific evidence","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-ended":[0],"scientific":[1,96,202],"discovery":[2,56,181,203],"with":[3,90,102,108,204],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"increasingly":[8],"operates":[9],"as":[10,53,70,143],"a":[11,20,50,55,59,71,92],"long-horizon":[12],"loop":[13],"of":[14,140],"hypothesis":[15,51],"search":[16,148,172,197,214],"and":[17,58,125,154,176,219],"verification,":[18],"where":[19],"reward":[21,60],"signal":[22],"guides":[23],"which":[24,35],"hypotheses":[25,112,156],"to":[26,86,113,149,169,194],"test":[27],"next.":[28],"A":[29],"notable":[30],"recent":[31],"example":[32],"is":[33,79,83],"AutoDiscovery,":[34],"uses":[36],"\"Bayesian":[37],"surprise\"":[38],"-":[39,52,81],"the":[40,170,195],"belief":[41,210],"shift":[42],"an":[43],"LLM":[44,104],"undergoes":[45],"after":[46],"observing":[47],"evidence":[48,109],"for":[49,61,94,117],"both":[54],"metric":[57],"search.":[62],"We":[63,98,120,145],"first":[64],"observe":[65],"that":[66,88,127,157,200,216],"AutoDiscovery":[67],"treats":[68],"surprisal":[69,75,116,188],"static":[72,141],"quantity,":[73],"while":[74],"in":[76],"human":[77],"reasoning":[78],"non-stationary":[80,115,161,187],"it":[82],"defined":[84],"relative":[85],"beliefs":[87],"evolve":[89],"experience,":[91],"prerequisite":[93],"continual":[95,201],"discovery.":[97],"address":[99],"this":[100],"mismatch":[101],"evidence-informed":[103],"beliefs:":[105],"priors":[106],"updated":[107],"from":[110],"previous":[111],"compute":[114],"new":[118],"hypotheses.":[119],"compare":[121],"in-context":[122],"belief-updating":[123],"mechanisms":[124],"find":[126],"embedding-based":[128],"retrieval-augmented":[129],"generation":[130],"over":[131],"prior":[132],"discoveries":[133],"best":[134],"anticipates":[135],"eventual":[136],"posteriors,":[137],"identifying":[138],"37.5%":[139],"surprisals":[142],"spurious.":[144],"then":[146],"modify":[147],"avoid":[150,217],"these":[151],"spurious":[152],"rewards":[153],"prioritize":[155],"remain":[158],"surprising":[159],"under":[160],"beliefs.":[162],"Concretely,":[163],"we":[164],"introduce":[165],"two":[166],"complementary":[167],"changes":[168],"original":[171,196],"procedure:":[173],"belief-update":[174],"filtering":[175],"diversity":[177],"maximization.":[178],"Across":[179],"five":[180],"domains,":[182],"our":[183],"method":[184],"increases":[185],"accumulated":[186],"by":[189],"30.62%":[190],"on":[191],"average":[192],"compared":[193],"procedure,":[198],"demonstrating":[199],"LLMs":[205],"requires":[206],"not":[207],"only":[208],"better":[209],"measurement":[211],"but":[212],"also":[213],"procedures":[215],"redundancy":[218],"encourage":[220],"diversity.":[221]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}