{"id":"https://openalex.org/W7166808485","doi":"https://doi.org/10.18653/v1/2026.findings-acl.388","title":"Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining","display_name":"Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166808485","doi":"https://doi.org/10.18653/v1/2026.findings-acl.388"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.388","doi":"https://doi.org/10.18653/v1/2026.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.388","pdf_url":"https://aclanthology.org/2026.findings-acl.388.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.388.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139758604","display_name":"Xiaofan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Zhou","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139743222","display_name":"Lu Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Cheng","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44116274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7891","last_page":"7908"},"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":0.4381999969482422,"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":0.4381999969482422,"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":0.24899999797344208,"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":0.11640000343322754,"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/conformal-prediction","display_name":"conformal prediction","score":0.8019999861717224},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9179999828338623},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9079999923706055},{"id":"https://openalex.org/keywords/question-clustering","display_name":"question clustering","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720000267028809},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.388","doi":"https://doi.org/10.18653/v1/2026.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.388","pdf_url":"https://aclanthology.org/2026.findings-acl.388.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.388","doi":"https://doi.org/10.18653/v1/2026.findings-acl.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.388","pdf_url":"https://aclanthology.org/2026.findings-acl.388.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5642320712","display_name":"Collaborative Research: III:  Medium: Knowledge discovery from highly heterogeneous, sparse and private data in biomedical informatics","funder_award_id":"2312862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5717765296","display_name":"SCH: Fair and Interpretable Prediction of Alzheimer's Disease and MCI using LLMs","funder_award_id":"1r01ag091762-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8221326746","display_name":"Collaborative Research: FDT-BioTech: Advancing Alzheimer's Disease Understanding and Treatments through Digital Twin Modeling","funder_award_id":"2533996","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8964793212","display_name":"CAREER: Conformal Methods for Responsible Language Models","funder_award_id":"2440542","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/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166808485.pdf","grobid_xml":"https://content.openalex.org/works/W7166808485.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392271198","https://openalex.org/W4412889571","https://openalex.org/W4410371768","https://openalex.org/W7204457146","https://openalex.org/W4414977715","https://openalex.org/W4399990130","https://openalex.org/W4415964470","https://openalex.org/W7154941992","https://openalex.org/W7212364591","https://openalex.org/W7154571449"],"abstract_inverted_index":{"Continual":[0],"Learning":[1],"(CL)":[2],"is":[3,87,174],"essential":[4],"for":[5,34,56,96],"enabling":[6],"self-evolving":[7],"large":[8,93],"language":[9],"models":[10],"(LLMs)":[11],"to":[12,29,145],"adapt":[13],"and":[14,109,166],"remain":[15],"effective":[16],"amid":[17],"rapid":[18],"knowledge":[19],"growth.Yet,":[20],"despite":[21],"its":[22,151],"importance,":[23],"little":[24],"attention":[25],"has":[26,49],"been":[27],"given":[28],"establishing":[30],"statistical":[31],"reliability":[32,167],"guarantees":[33,55],"LLMs":[35],"under":[36,75,170],"CL,":[37],"particularly":[38],"in":[39,52,63,122],"the":[40,116,123,133,143,164],"setting":[41],"of":[42,118,168],"continual":[43],"domain":[44,73],"pretraining":[45],"(CDP).Conformal":[46],"Prediction":[47],"(CP)":[48],"shown":[50],"promise":[51],"offering":[53],"correctness":[54],"LLMs,":[57],"but":[58],"it":[59],"faces":[60],"major":[61],"challenges":[62],"CDP:":[64],"testing":[65],"data":[66,135],"often":[67],"stems":[68],"from":[69,148],"unknown":[70],"or":[71,131,153],"shifting":[72],"distributions,":[74],"which":[76],"CP":[77,89,111,141,169],"may":[78],"no":[79],"longer":[80],"provide":[81],"valid":[82],"guarantees.Moreover,":[83],"when":[84,150],"high":[85],"coverage":[86],"required,":[88],"can":[90],"yield":[91],"excessively":[92],"prediction":[94],"sets":[95],"unanswerable":[97],"queries,":[98],"reducing":[99],"informativeness.To":[100],"address":[101],"these":[102],"challenges,":[103],"we":[104],"introduce":[105],"an":[106],"adaptive":[107,139],"rejection":[108,140],"non-exchangeable":[110],"framework.Our":[112],"method":[113],"first":[114],"estimates":[115],"distribution":[117],"questions":[119],"across":[120],"domains":[121],"test":[124],"set":[125],"using":[126],"transformer-based":[127],"clustering,":[128],"then":[129],"reweights":[130],"resamples":[132],"calibration":[134],"accordingly.Building":[136],"on":[137],"this,":[138],"allows":[142],"LLM":[144],"selectively":[146],"abstain":[147],"answering":[149],"confidence":[152],"competence":[154],"shifts":[155],"significantly.Extensive":[156],"experiments":[157],"demonstrate":[158],"that":[159],"our":[160],"framework":[161],"enhances":[162],"both":[163],"effectiveness":[165],"CDP":[171],"scenarios.Our":[172],"code":[173],"available":[175],"at:":[176],"https://github.com/AlearZhou/CPCL20":[177],"40":[178],"60":[179],"80":[180],"Quantile":[181],"(%)":[182],"0.0":[183],"0.1":[184],"0.2":[185],"0.3":[186],"0.4":[187],"0.5":[188],"0.6":[189],"0.7":[190],"0.":[191]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}