{"id":"https://openalex.org/W7165401962","doi":"https://doi.org/10.48550/arxiv.2606.19353","title":"Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence","display_name":"Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7165401962","doi":"https://doi.org/10.48550/arxiv.2606.19353"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19353","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,"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":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.2606.19353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111037265","display_name":"Jinseok Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Jinseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046791832","display_name":"Minkyoung Song","orcid":"https://orcid.org/0000-0002-5732-4239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Minkyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110582167","display_name":"Hyunji Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Hyunji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058910905","display_name":"N Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Namhoon","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2517000138759613,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2517000138759613,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1446000039577484,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.1339000016450882,"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/interpretability","display_name":"Interpretability","score":0.8668000102043152},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.6456000208854675},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5146999955177307},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.508899986743927},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4812999963760376},{"id":"https://openalex.org/keywords/uncertainty-reduction-theory","display_name":"Uncertainty reduction theory","score":0.4498000144958496},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8668000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557000279426575},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.608299970626831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5566999912261963},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.40639999508857727},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40220001339912415},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3481000065803528},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C176147448","wikidata":"https://www.wikidata.org/wiki/Q1889114","display_name":"Sensitivity analysis","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19353","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.19353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19353","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,"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":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":{"In-Context":[0],"Learning":[1],"(ICL)":[2],"allows":[3],"LLMs":[4],"to":[5,7,24,32,66,99,159,185],"adapt":[6],"new":[8,171,231],"tasks":[9,178],"from":[10,40,49,166],"a":[11,18,78,110,117,217,230],"few":[12],"demonstrations,":[13],"but":[14],"its":[15],"reliability":[16],"remains":[17],"concern:":[19],"predictions":[20,199],"are":[21],"highly":[22],"sensitive":[23],"both":[25],"prompt":[26],"design":[27],"and":[28,87,120,136,145,164,182],"the":[29,34,68,88,101,122,131,143,235,241],"model's":[30],"ability":[31],"understand":[33],"context,":[35],"obscuring":[36],"whether":[37],"failures":[38],"arise":[39],"data":[41,151],"properties":[42],"or":[43,127],"model":[44,97,100,245],"limitations.":[45],"Uncertainty":[46],"decomposition-separating":[47],"aleatoric":[48,114,161],"epistemic":[50,167],"sources-is":[51],"particularly":[52],"crucial":[53],"in":[54,149,154,176],"this":[55,170],"setting,":[56],"yet":[57],"existing":[58,206],"methods,":[59],"designed":[60],"for":[61,179,220,233],"standard":[62],"generation":[63],"tasks,":[64],"fail":[65],"capture":[67],"unique":[69],"dynamics":[70],"of":[71,80,91,113,133,197,238,244],"ICL.":[72,92],"To":[73],"address":[74],"this,":[75],"we":[76,140,188,210],"introduce":[77],"concept":[79,103],"self-function":[81],"vectors,":[82],"built":[83],"upon":[84],"Bayesian":[85,118],"views":[86],"mechanistic":[89,242],"interpretability":[90],"These":[93],"vectors":[94],"leverage":[95],"internal":[96],"representations":[98],"latent":[102],"learned":[104],"during":[105],"in-context":[106],"prompting,":[107],"thereby":[108],"enabling":[109],"direct":[111],"estimation":[112],"uncertainty":[115,162,196,239],"within":[116],"framework":[119],"circumventing":[121],"reliance":[123],"on":[124],"brittle":[125],"input":[126],"decoding":[128],"manipulations.":[129],"Given":[130],"lack":[132],"established":[134],"benchmarks":[135],"suitable":[137],"evaluation":[138,147,172],"protocols,":[139],"also":[141],"propose":[142],"first":[144],"rigorous":[146],"protocol,":[148],"which":[150],"is":[152],"manipulated":[153],"controlled":[155],"ways":[156],"so":[157],"as":[158,216,224],"quantify":[160],"precisely":[163],"separately":[165],"uncertainty.":[168],"With":[169],"framework,":[173],"initially":[174],"grounded":[175],"synthetic":[177],"conceptual":[180],"development":[181],"subsequently":[183],"extended":[184],"real-world":[186],"datasets,":[187],"show":[189,211],"that":[190],"our":[191],"proposed":[192],"methodology":[193],"can":[194,213],"measure":[195],"LLM":[198],"made":[200],"under":[201],"ICL":[202],"more":[203],"reliably":[204],"than":[205],"alternative":[207],"methods.":[208],"Moreover,":[209],"it":[212],"be":[214],"used":[215],"practical":[218],"tool":[219],"trustworthy-related":[221],"applications,":[222],"such":[223],"hallucination":[225],"detection.":[226],"Our":[227],"findings":[228],"pave":[229],"direction":[232],"connecting":[234],"quantitative":[236],"view":[237],"with":[240],"understanding":[243],"behavior.":[246]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-20T00:00:00"}