{"id":"https://openalex.org/W7152702868","doi":"https://doi.org/10.48550/arxiv.2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","display_name":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7152702868","doi":"https://doi.org/10.48550/arxiv.2604.06262"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06262","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133286098","display_name":"Chuang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133306909","display_name":"Hongke Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hongke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133305990","display_name":"Xiaofang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xiaofang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133309390","display_name":"Xiaomeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaomeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.5710999965667725,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.5710999965667725,"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":0.09619999676942825,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06849999725818634,"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/inference","display_name":"Inference","score":0.6571999788284302},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.585099995136261},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39989998936653137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.396699994802475},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.34529998898506165},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3422999978065491},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3075000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307000160217285},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176999807357788},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5029000043869019},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39989998936653137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25290000438690186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06262","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06262","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7410953044891357,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contextual":[0],"clinical":[1,10,173],"reasoning":[2,155],"demands":[3],"robust":[4],"inference":[5,47],"grounded":[6],"in":[7],"complex,":[8],"heterogeneous":[9],"records.":[11],"While":[12],"state-of-the-art":[13,185],"fine-tuning,":[14],"in-context":[15],"learning":[16,193],"(ICL),":[17],"and":[18,141],"retrieval-augmented":[19],"generation":[20],"(RAG)":[21],"enable":[22],"knowledge":[23,64],"exposure,":[24,85],"they":[25],"often":[26],"fall":[27],"short":[28],"of":[29,43,165],"genuine":[30],"contextual":[31],"internalization:":[32],"dynamically":[33],"adjusting":[34],"a":[35,57,91,148],"model's":[36],"internal":[37,142],"representations":[38],"to":[39,66,103,134,161,191],"the":[40,86,108,132,136,154,166],"subtle":[41],"nuances":[42],"individual":[44],"cases":[45],"at":[46,127],"time.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"Dual-Stream":[54],"Calibration":[55,88,110],"(DSC),":[56],"test-time":[58,192],"training":[59,122],"framework":[60],"that":[61],"transcends":[62],"superficial":[63],"exposure":[65],"achieve":[67],"deep":[68],"internalization":[69,75],"during":[70],"inference.":[71],"DSC":[72,175],"facilitates":[73],"input":[74],"by":[76,100],"synergistically":[77],"aligning":[78],"two":[79],"calibration":[80],"streams.":[81],"Unlike":[82],"passive":[83,158],"context":[84],"Semantic":[87],"Stream":[89,111],"enforces":[90],"deliberative":[92],"reflection":[93],"on":[94,123],"core":[95],"evidence,":[96],"internalizing":[97],"semantic":[98],"anchors":[99],"minimizing":[101],"entropy":[102],"stabilize":[104],"generative":[105],"trajectories.":[106],"Simultaneously,":[107],"Structural":[109],"assimilates":[112],"latent":[113,167],"inferential":[114,168],"dependencies":[115],"through":[116],"an":[117,162],"iterative":[118],"meta-learning":[119],"objective.":[120],"By":[121],"specialized":[124],"support":[125],"sets":[126],"test-time,":[128],"this":[129],"stream":[130],"enables":[131],"model":[133],"bridge":[135],"gap":[137],"between":[138],"external":[139],"evidence":[140],"logic,":[143],"synthesizing":[144],"fragmented":[145],"data":[146],"into":[147],"coherent":[149],"response.":[150],"Our":[151],"approach":[152],"shifts":[153],"paradigm":[156],"from":[157,188],"attention-based":[159],"matching":[160],"active":[163],"refinement":[164],"space.":[169],"Validated":[170],"against":[171],"thirteen":[172],"datasets,":[174],"demonstrates":[176],"superiority":[177],"across":[178],"three":[179],"distinct":[180],"task":[181],"paradigms,":[182],"consistently":[183],"outstripping":[184],"baselines":[186],"ranging":[187],"training-dependent":[189],"models":[190],"frameworks.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}