{"id":"https://openalex.org/W7161798567","doi":"https://doi.org/10.48550/arxiv.2605.18792","title":"Trust or Abstain? A Self-Aware RAG Approach","display_name":"Trust or Abstain? A Self-Aware RAG Approach","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7161798567","doi":"https://doi.org/10.48550/arxiv.2605.18792"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18792","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18792","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.2605.18792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136562093","display_name":"Xi Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136573723","display_name":"Ziqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ziqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136599688","display_name":"Kai Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136521934","display_name":"Wujiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wujiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136606641","display_name":"Minghao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136557483","display_name":"Bangji Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bangji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136573338","display_name":"Jiajun Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136570905","display_name":"Dimitris N. Metaxas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metaxas, Dimitris N.","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":0.5325000286102295,"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":0.5325000286102295,"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":0.1647000014781952,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08449999988079071,"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/path","display_name":"Path (computing)","score":0.503600001335144},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.491100013256073},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48330000042915344},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345999836921692},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4336000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C31084985","wikidata":"https://www.wikidata.org/wiki/Q372650","display_name":"Common knowledge (logic)","level":5,"score":0.3465999960899353},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18792","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18792","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.2605.18792","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18792","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5200052857398987}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"improves":[3,159],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"by":[8,81],"incorporating":[9],"external":[10],"evidence,":[11],"but":[12],"it":[13],"also":[14],"introduces":[15],"knowledge":[16,21,25,67],"conflicts":[17],"when":[18],"retrieved":[19],"contextual":[20],"(CK)":[22],"and":[23,68,87,124,162,168,193],"parametric":[24],"(PK)":[26],"disagree":[27],"or":[28,152],"are":[29],"both":[30],"unreliable.":[31],"Existing":[32],"approaches":[33],"mainly":[34],"coordinate":[35],"which":[36],"source":[37],"to":[38,60,140],"use,":[39],"without":[40],"explicitly":[41],"asking":[42],"whether":[43],"each":[44],"answer":[45,89,194],"path":[46],"is":[47,198],"correct.":[48],"We":[49,103],"argue":[50],"that":[51,113],"faithful":[52],"RAG":[53,112],"requires":[54,114],"LLM":[55,83,116,156],"self-awareness,":[56],"namely":[57],"the":[58,62,172],"ability":[59],"recognize":[61],"limits":[63],"of":[64],"its":[65],"own":[66],"reasoning.":[69],"To":[70],"ground":[71],"this":[72],"problem,":[73],"we":[74],"construct":[75],"a":[76,107,120,142,188],"model-specific,":[77],"ground-truth-aligned":[78],"knowledge-conflict":[79],"benchmark":[80],"evaluating":[82],"backbones":[84],"on":[85,175],"PK-only":[86],"CK-conditioned":[88],"paths":[90],"over":[91,145,165],"approximately":[92],"69K":[93],"query-context":[94],"instances":[95],"per":[96],"backbone,":[97],"drawn":[98],"from":[99,129],"five":[100],"conflict-QA":[101],"datasets.":[102,177],"then":[104,132],"introduce":[105],"SABER,":[106],"Self-Aware":[108],"Belief":[109],"Estimator":[110],"for":[111],"no":[115],"fine-tuning.":[117],"SABER":[118,158],"combines":[119],"self-prior":[121],"with":[122,136,171],"PK-side":[123],"CK-side":[125],"conditional":[126],"reasoning":[127],"representations":[128],"multi-trace":[130],"inference,":[131],"estimates":[133],"reliability":[134],"beliefs":[135],"two":[137],"lightweight":[138],"predictors":[139],"drive":[141],"4-cell":[143],"decision":[144],"trust":[146,148,150],"PK,":[147],"CK,":[149],"either,":[151],"abstain.":[153],"Across":[154],"four":[155],"backbones,":[157],"end-to-end":[160],"accuracy":[161],"conflict-specific":[163],"faithfulness":[164],"ten":[166],"inference-time":[167],"fine-tuning":[169],"baselines,":[170],"largest":[173],"gains":[174],"conflict-heavy":[176],"Under":[178],"abstention,":[179],"SABER's":[180],"risk-coverage":[181],"curve":[182],"Pareto-dominates":[183],"every":[184],"prompt-based":[185],"abstainer,":[186],"providing":[187],"tunable":[189],"balance":[190],"between":[191],"coverage":[192],"risk.":[195],"Our":[196],"code":[197],"available":[199],"at":[200],"https://github.com/xizhu1022/SABER.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}