{"id":"https://openalex.org/W7204246190","doi":"https://doi.org/10.18653/2026.emnlp-main.664","title":"The RAT: A Unified Bayesian Model for RAG Evaluation","display_name":"The RAT: A Unified Bayesian Model for RAG Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204246190","doi":"https://doi.org/10.18653/2026.emnlp-main.664"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.664","doi":"https://doi.org/10.18653/2026.emnlp-main.664","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.664","pdf_url":"https://aclanthology.org/2026.emnlp-main.664.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.664.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078207868","display_name":"Pius von D\u00e4niken","orcid":"https://orcid.org/0000-0001-8339-5543","observed_orcids":["https://orcid.org/0000-0001-8339-5543"]},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pius von D\u00e4niken","raw_affiliation_strings":["Centre for Artificial Intelligence ZHAW School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence ZHAW School of Engineering","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130357417","display_name":"Felix Matthias Saaro","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Matthias Saaro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077273985","display_name":"Mark Cieliebak","orcid":"https://orcid.org/0009-0007-3059-8516","observed_orcids":["https://orcid.org/0009-0007-3059-8516"]},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mark Cieliebak","raw_affiliation_strings":["Centre for Artificial Intelligence ZHAW School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence ZHAW School of Engineering","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018584668","display_name":"Jan Deriu","orcid":"https://orcid.org/0000-0002-8405-1344","observed_orcids":["https://orcid.org/0000-0002-8405-1344"]},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jan Milan Deriu","raw_affiliation_strings":["Centre for Artificial Intelligence ZHAW School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence ZHAW School of Engineering","institution_ids":["https://openalex.org/I858936495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68343943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15295","last_page":"15310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6753000020980835,"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":0.6753000020980835,"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":0.28439998626708984,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.015599999576807022,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9789999723434448},{"id":"https://openalex.org/keywords/rag-evaluation","display_name":"RAG evaluation","score":0.9919999837875366},{"id":"https://openalex.org/keywords/retrieval-success","display_name":"retrieval success","score":0.5929999947547913},{"id":"https://openalex.org/keywords/answer-correctness","display_name":"answer correctness","score":0.9710000157356262},{"id":"https://openalex.org/keywords/error-propagation","display_name":"error propagation","score":0.675000011920929},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.8100000023841858},{"id":"https://openalex.org/keywords/noisy-measurements","display_name":"noisy measurements","score":0.531000018119812},{"id":"https://openalex.org/keywords/information-theoretic-analysis","display_name":"information-theoretic analysis","score":0.550000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6603999733924866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5777000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48420000076293945},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.664","doi":"https://doi.org/10.18653/2026.emnlp-main.664","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.664","pdf_url":"https://aclanthology.org/2026.emnlp-main.664.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.24753","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24753","pdf_url":"https://arxiv.org/pdf/2608.24753","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24753","doi":"https://doi.org/10.48550/arxiv.2608.24753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24753","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.664","doi":"https://doi.org/10.18653/2026.emnlp-main.664","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.664","pdf_url":"https://aclanthology.org/2026.emnlp-main.664.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204246190.pdf","grobid_xml":"https://content.openalex.org/works/W7204246190.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415798436","https://openalex.org/W7120272428","https://openalex.org/W4416048488","https://openalex.org/W7166659534","https://openalex.org/W4416035704","https://openalex.org/W7204536999","https://openalex.org/W4415017642","https://openalex.org/W4388787625","https://openalex.org/W7171290893","https://openalex.org/W7171803912"],"abstract_inverted_index":{"Evaluating":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"systems":[4,94],"requires":[5],"assessing":[6],"not":[7],"only":[8],"end-to-end":[9],"correctness":[10],"but":[11],"also":[12],"how":[13,18],"individual":[14],"components":[15],"interact":[16],"and":[17,36,80,83,121],"errors":[19],"propagate":[20],"through":[21],"the":[22,42,50,60,65,69,86,103,131],"pipeline.We":[23],"introduce":[24],"a":[25,53,153],"Bayesian":[26],"evaluation":[27],"framework":[28,70],"that":[29,85,95,108],"jointly":[30],"models":[31],"retrieval":[32,66],"success,":[33,58],"abstention":[34],"behavior,":[35],"answer":[37],"correctness,":[38],"factorized":[39],"according":[40],"to":[41,71,133,143],"pipeline's":[43],"information":[44],"flow.The":[45],"model":[46,132],"distinguishes":[47],"task":[48],"success.Whether":[49],"user":[51],"received":[52],"correct":[54],"answer,":[55],"from":[56],"generator":[57,61],"whether":[59],"behaved":[62],"appropriately":[63],"given":[64],"outcome.We":[67],"apply":[68],"27":[72],"RAG":[73],"configurations":[74],"across":[75],"three":[76,78,81],"datasets,":[77],"retrievers,":[79],"generators,":[82],"show":[84],"conditional":[87],"decomposition":[88],"reveals":[89],"substantial":[90],"behavioral":[91],"differences":[92],"between":[93],"appear":[96],"equivalent":[97],"under":[98],"marginal":[99],"metrics.We":[100],"further":[101],"analyze":[102],"annotation":[104],"allocation":[105],"problem,":[106],"demonstrating":[107],"retrieval-success":[109],"annotations":[110,116,136],"are":[111],"more":[112],"informative":[113],"than":[114],"task-success":[115],"for":[117,126],"estimating":[118],"policy":[119],"adherence,":[120],"provide":[122],"an":[123],"information-theoretic":[124],"explanation":[125],"this":[127],"asymmetry.Finally,":[128],"we":[129],"extend":[130],"incorporate":[134],"LLM-as-a-judge":[135],"as":[137],"calibrated":[138],"noisy":[139],"observations,":[140],"enabling":[141],"practitioners":[142],"combine":[144],"limited":[145],"human":[146],"judgments":[147],"with":[148],"cheaper":[149],"automated":[150],"assessments":[151],"within":[152],"unified":[154],"probabilistic":[155],"model.":[156]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-08-27T00:00:00"}