{"id":"https://openalex.org/W7151432850","doi":"https://doi.org/10.48550/arxiv.2604.03925","title":"AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference","display_name":"AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference","publication_year":2026,"publication_date":"2026-04-05","ids":{"openalex":"https://openalex.org/W7151432850","doi":"https://doi.org/10.48550/arxiv.2604.03925"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03925","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133097992","display_name":"Fangzhou Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Fangzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133098002","display_name":"Peiran Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Peiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133133147","display_name":"Shuo Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133082246","display_name":"Siyuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Siyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124943304","display_name":"Qianwen Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Qianwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133077636","display_name":"Kazunori Yamada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamada, Kazunori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133093136","display_name":"Ziming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ziming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077612510","display_name":"Haichong K. Zhang","orcid":"https://orcid.org/0000-0002-1314-8456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haichong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133112733","display_name":"Zhengzhong Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Zhengzhong","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2653999924659729,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2653999924659729,"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":0.11599999666213989,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0868000015616417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5687999725341797},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5349000096321106},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5091999769210815},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5076000094413757},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.37940001487731934},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.3531000018119812},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3529999852180481},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5091999769210815},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3199999928474426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C2779377595","wikidata":"https://www.wikidata.org/wiki/Q21045424","display_name":"Approximate Bayesian computation","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03925","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03925","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":"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":{"Large":[0],"language":[1],"models":[2,139],"struggle":[3],"to":[4,14,99],"accumulate":[5],"evidence":[6,104],"across":[7,108],"multiple":[8],"rounds":[9],"of":[10],"user":[11,31,170],"interaction,":[12],"failing":[13],"update":[15],"their":[16,35],"beliefs":[17],"in":[18,37,161],"a":[19,43,54,58,62,67],"manner":[20],"consistent":[21],"with":[22,143],"Bayesian":[23,59,137],"inference.":[24],"Existing":[25],"solutions":[26],"require":[27],"fine-tuning":[28,160],"on":[29,118,140,168],"sensitive":[30,169],"interaction":[32,148],"data,":[33],"limiting":[34],"applicability":[36],"privacy-conscious":[38],"settings.":[39],"We":[40,106],"propose":[41],"AdaptFuse,":[42],"training-free":[44],"framework":[45],"that":[46,153],"externalizes":[47],"probabilistic":[48],"computation":[49],"entirely":[50],"from":[51,96],"the":[52,97,100,173],"LLM:":[53],"symbolic":[55,101],"module":[56],"maintains":[57],"posterior":[60,102],"over":[61,147],"discrete":[63],"hypothesis":[64],"set,":[65],"while":[66],"frozen":[68],"LLM":[69,98],"contributes":[70],"semantic":[71],"reasoning":[72],"via":[73],"multi-sample":[74],"Dirichlet":[75],"aggregation.":[76],"The":[77],"two":[78],"signals":[79],"are":[80],"combined":[81],"through":[82],"entropy-adaptive":[83],"fusion,":[84],"which":[85],"automatically":[86],"weights":[87],"each":[88],"source":[89],"by":[90],"its":[91],"predictive":[92],"confidence,":[93],"shifting":[94],"reliance":[95],"as":[103],"accumulates.":[105],"evaluate":[107],"three":[109],"domains:":[110],"flight":[111],"recommendation,":[112,114,163],"hotel":[113],"and":[115,125,135,175],"web":[116],"shopping;":[117],"Gemma":[119],"2":[120],"9B,":[121],"Llama":[122],"3":[123],"8B,":[124],"Qwen":[126],"2.5":[127],"7B.":[128],"AdaptFuse":[129],"consistently":[130],"outperforms":[131],"both":[132],"prompting":[133],"baselines":[134],"fine-tuned":[136],"Teaching":[138],"all":[141],"tasks,":[142],"accuracy":[144],"improving":[145],"monotonically":[146],"rounds.":[149],"These":[150],"results":[151],"demonstrate":[152],"principled":[154],"inference-time":[155],"algorithms":[156],"can":[157],"substitute":[158],"for":[159],"personalized":[162],"without":[164],"storing":[165],"or":[166],"training":[167],"data.":[171],"All":[172],"code":[174],"materials":[176],"will":[177],"be":[178],"open-sourced.":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}