{"id":"https://openalex.org/W7140166157","doi":"https://doi.org/10.48550/arxiv.2603.21172","title":"Entropy Alone is Insufficient for Safe Selective Prediction in LLMs","display_name":"Entropy Alone is Insufficient for Safe Selective Prediction in LLMs","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140166157","doi":"https://doi.org/10.48550/arxiv.2603.21172"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21172","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.2603.21172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Phillips, Edward","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phillips, Edward","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gustafsson, Fredrik K.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gustafsson, Fredrik K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Sean","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Sean","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thakur, Anshul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakur, Anshul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Clifton, David A.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clifton, David A.","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.28690001368522644,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.28690001368522644,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2012999951839447,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.14730000495910645,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6169999837875366},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.551800012588501},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5102999806404114},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.4284999966621399},{"id":"https://openalex.org/keywords/measurement-uncertainty","display_name":"Measurement uncertainty","score":0.35429999232292175}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5737000107765198},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21172","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.2603.21172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21172","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Selective":[0],"prediction":[1,39],"systems":[2],"can":[3,128],"mitigate":[4],"harms":[5],"resulting":[6],"from":[7,13],"language":[8],"model":[9,91],"hallucinations":[10],"by":[11,70],"abstaining":[12],"answering":[14],"in":[15,32],"high-risk":[16],"cases.":[17],"Uncertainty":[18],"quantification":[19],"techniques":[20],"are":[21,29],"often":[22],"employed":[23],"to":[24,44,63,106,131],"identify":[25,52],"such":[26],"cases,":[27],"but":[28],"rarely":[30],"evaluated":[31],"the":[33,36,93,99,112],"context":[34],"of":[35,57,114,117],"wider":[37],"selective":[38],"policy":[40],"and":[41,67,89,102],"its":[42],"ability":[43],"operate":[45,132],"at":[46,133],"low":[47],"target":[48],"error":[49],"rates.":[50],"We":[51,79],"a":[53,75,126,134],"model-dependent":[54],"failure":[55],"mode":[56],"entropy-based":[58],"uncertainty":[59,118],"methods":[60],"that":[61,81,122],"leads":[62],"unreliable":[64],"abstention":[65],"behaviour,":[66],"address":[68],"it":[69],"combining":[71],"entropy":[72],"scores":[73],"with":[74],"correctness":[76],"probe":[77],"signal.":[78],"find":[80],"across":[82],"three":[83],"QA":[84],"benchmarks":[85],"(TriviaQA,":[86],"BioASQ,":[87],"MedicalQA)":[88],"four":[90],"families,":[92],"combined":[94],"score":[95],"generally":[96],"improves":[97],"both":[98],"risk--coverage":[100],"trade-off":[101],"calibration":[103],"performance":[104],"relative":[105],"entropy-only":[107],"baselines.":[108],"Our":[109],"results":[110],"highlight":[111],"importance":[113],"deployment-facing":[115],"evaluation":[116],"methods,":[119],"using":[120],"metrics":[121],"directly":[123],"reflect":[124],"whether":[125],"system":[127],"be":[129],"trusted":[130],"stated":[135],"risk":[136],"level.":[137]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}