{"id":"https://openalex.org/W7163191002","doi":"https://doi.org/10.48550/arxiv.2606.00432","title":"Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG","display_name":"Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163191002","doi":"https://doi.org/10.48550/arxiv.2606.00432"},"language":"en","primary_location":{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/106870","is_oa":false,"landing_page_url":"https://dr.lib.iastate.edu/handle/20.500.12876/106870","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.48550/arXiv.2606.00432","raw_type":"preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00432","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137705571","display_name":"Ibne Farabi Shihab","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihab, Ibne Farabi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122389296","display_name":"Fariya Afrin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Afrin, Fariya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119832027","display_name":"Sanjeda Akter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akter, Sanjeda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137626995","display_name":"Anuj Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Anuj","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/T10028","display_name":"Topic Modeling","score":0.8917999863624573,"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/T10028","display_name":"Topic Modeling","score":0.8917999863624573,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.019099999219179153,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.0142000000923872,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5534999966621399},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.49309998750686646},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.46790000796318054},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4562999904155731},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.42089998722076416},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4025999903678894},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.3774000108242035}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48240000009536743},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38100001215934753},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C39947850","wikidata":"https://www.wikidata.org/wiki/Q729523","display_name":"Geometric distribution","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.2630999982357025}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/106870","is_oa":false,"landing_page_url":"https://dr.lib.iastate.edu/handle/20.500.12876/106870","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.48550/arXiv.2606.00432","raw_type":"preprint"},{"id":"doi:10.48550/arxiv.2606.00432","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00432","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.2606.00432","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00432","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6801173686981201}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"retrieval-augmented":[1],"generation":[2,69],"(RAG)":[3],"systems":[4],"scale,":[5],"it":[6],"becomes":[7],"increasingly":[8],"challenging":[9],"to":[10,41,109,206],"ensure":[11],"faithful":[12,211],"grounding":[13,133,146,160],"in":[14,45,178],"external":[15],"evidence.":[16],"Large":[17],"language":[18],"models":[19],"may":[20],"still":[21],"prioritize":[22],"parametric":[23],"knowledge":[24],"over":[25,113,184],"retrieved":[26,80,93,143],"information":[27],"when":[28,131],"conflicts":[29],"arise.":[30],"We":[31,149],"propose":[32],"a":[33,57,72,87,110,118,152,201],"novel":[34],"training-free":[35],"decoding":[36],"framework,":[37],"\\emph{Grounded":[38],"Decoding},":[39],"designed":[40],"improve":[42],"factual":[43,179],"consistency":[44],"RAG":[46,74,130,186,212],"without":[47],"modifying":[48],"model":[49],"parameters.":[50],"Unlike":[51],"standard":[52,129,185],"approaches":[53],"that":[54,157,197],"rely":[55],"on":[56,77,92,162,169],"single":[58],"conditional":[59],"distribution,":[60],"our":[61],"method":[62],"constructs":[63],"two":[64,124],"matched-prompt":[65],"distributions":[66],"at":[67],"every":[68],"step:":[70],"(1)":[71],"full":[73],"distribution":[75,89,102],"conditioned":[76,90],"the":[78,96,106,114,123,132],"query,":[79],"documents,":[81],"and":[82,85,95,137,165,173,181,187,203],"generated":[83],"prefix,":[84],"(2)":[86],"retrieval-only":[88],"solely":[91],"evidence":[94,144],"same":[97],"prefix.":[98],"The":[99],"final":[100],"next-token":[101],"is":[103,135],"derived":[104],"as":[105,145],"unique":[107],"solution":[108],"KL-barycenter":[111],"objective":[112],"probability":[115,140],"simplex,":[116],"yielding":[117],"normalized":[119],"geometric":[120],"fusion":[121,199],"of":[122],"distributions.This":[125],"formulation":[126],"naturally":[127],"recovers":[128],"weight":[134],"zero":[136],"smoothly":[138],"shifts":[139],"mass":[141],"toward":[142],"strength":[147],"increases.":[148],"further":[150],"introduce":[151],"conflict-aware":[153],"adaptive":[154],"weighting":[155],"scheme":[156],"dynamically":[158],"adjusts":[159],"based":[161],"distributional":[163],"disagreement":[164],"retriever":[166],"confidence.":[167],"Experiments":[168],"ALCE,":[170],"Natural":[171],"Questions,":[172],"FActScore":[174],"demonstrate":[175],"consistent":[176],"improvements":[177],"accuracy":[180],"citation":[182],"quality":[183],"competitive":[188],"decoding-time":[189],"baselines,":[190],"while":[191],"maintaining":[192],"fluency.":[193],"Our":[194],"results":[195],"indicate":[196],"probability-level":[198],"provides":[200],"strong":[202],"efficient":[204],"alternative":[205],"logit-level":[207],"intervention":[208],"methods":[209],"for":[210],"decoding.":[213]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-03T00:00:00"}