{"id":"https://openalex.org/W7166817804","doi":"https://doi.org/10.18653/v1/2026.acl-long.95","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":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166817804","doi":"https://doi.org/10.18653/v1/2026.acl-long.95"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.95","pdf_url":"https://aclanthology.org/2026.acl-long.95.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.95.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111037265","display_name":"Jinseok Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinseok Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139795267","display_name":"Minkyoung Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minkyoung Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821709","display_name":"Hyunji Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunji Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023840015","display_name":"Namhoon Lee","orcid":"https://orcid.org/0009-0001-5208-2007"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namhoon Lee","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7958423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2090","last_page":"2108"},"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":0.19099999964237213,"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":0.19099999964237213,"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":0.18060000240802765,"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":0.11569999903440475,"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/measure","display_name":"Measure (data warehouse)","score":0.6330000162124634},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3027999997138977},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.27469998598098755},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.2734000086784363},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.492900013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4156000018119812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.95","pdf_url":"https://aclanthology.org/2026.acl-long.95.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.95","pdf_url":"https://aclanthology.org/2026.acl-long.95.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4841618239879608,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1398259286","display_name":null,"funder_award_id":"RS-2019II191906","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1448736063","display_name":null,"funder_award_id":"RS-2023-00216011","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3415549828","display_name":null,"funder_award_id":"RS-2022-II220959","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3812690899","display_name":null,"funder_award_id":"RS-2023","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5051746381","display_name":null,"funder_award_id":"2019-II191906","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7294048361","display_name":null,"funder_award_id":"RS-2019-II191906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321282","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166817804.pdf","grobid_xml":"https://content.openalex.org/works/W7166817804.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In-Context":[0],"Learning":[1],"(ICL)":[2],"allows":[3],"LLMs":[4],"to":[5,7,24,32,65,96,155,180],"adapt":[6],"new":[8,166,224],"tasks":[9,173],"from":[10,40,48,162],"a":[11,18,76,107,114,211,223],"few":[12],"demonstrations,":[13],"but":[14],"its":[15],"reliability":[16],"remains":[17],"concern:":[19],"predictions":[20,194],"are":[21],"highly":[22],"sensitive":[23],"both":[25],"prompt":[26],"design":[27],"and":[28,85,117,132,141,160,177],"the":[29,34,67,86,98,119,127,139,228,234],"model's":[30],"ability":[31],"understand":[33],"context,":[35],"obscuring":[36],"whether":[37],"failures":[38],"arise":[39],"data":[41,147],"properties":[42],"or":[43,124],"model":[44,94,97,238],"limitations.Uncertainty":[45],"decomposition-separating":[46],"aleatoric":[47,111,157],"epistemic":[49,163],"sources-is":[50],"particularly":[51],"crucial":[52],"in":[53,145,150,171],"this":[54,165],"setting,":[55],"yet":[56],"existing":[57,201],"methods,":[58],"designed":[59],"for":[60,174,214,226],"standard":[61],"generation":[62],"tasks,":[63],"fail":[64],"capture":[66],"unique":[68],"dynamics":[69],"of":[70,78,89,110,129,192,231,237],"ICL.To":[71],"address":[72],"this,":[73],"we":[74,136,183,204],"introduce":[75],"concept":[77,100],"self-function":[79],"vectors,":[80],"built":[81],"upon":[82],"Bayesian":[83,115],"views":[84],"mechanistic":[87,235],"interpretability":[88],"ICL.These":[90],"vectors":[91],"leverage":[92],"internal":[93],"representations":[95],"latent":[99],"learned":[101],"during":[102],"in-context":[103],"prompting,":[104],"thereby":[105],"enabling":[106],"direct":[108],"estimation":[109],"uncertainty":[112,158,191,232],"within":[113],"framework":[116],"circumventing":[118],"reliance":[120],"on":[121],"brittle":[122],"input":[123],"decoding":[125],"manipulations.Given":[126],"lack":[128],"established":[130],"benchmarks":[131],"suitable":[133],"evaluation":[134,143,167],"protocols,":[135],"also":[137],"propose":[138],"first":[140],"rigorous":[142],"protocol,":[144],"which":[146],"is":[148],"manipulated":[149],"controlled":[151],"ways":[152],"so":[153],"as":[154,210,218],"quantify":[156],"precisely":[159],"separately":[161],"uncertainty.With":[164],"framework,":[168],"initially":[169],"grounded":[170],"synthetic":[172],"conceptual":[175],"development":[176],"subsequently":[178],"extended":[179],"real-world":[181],"datasets,":[182],"show":[184,205],"that":[185],"our":[186],"proposed":[187],"methodology":[188],"can":[189,207],"measure":[190],"LLM":[193],"made":[195],"under":[196],"ICL":[197],"more":[198],"reliably":[199],"than":[200],"alternative":[202],"methods.Moreover,":[203],"it":[206],"be":[208],"used":[209],"practical":[212],"tool":[213],"trustworthy-related":[215],"applications,":[216],"such":[217],"hallucination":[219],"detection.Our":[220],"findings":[221],"pave":[222],"direction":[225],"connecting":[227],"quantitative":[229],"view":[230],"with":[233],"understanding":[236],"behavior.":[239]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2026-07-02T00:00:00"}