{"id":"https://openalex.org/W7167898652","doi":"https://doi.org/10.1145/3805712.3808493","title":"Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems","display_name":"Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167898652","doi":"https://doi.org/10.1145/3805712.3808493"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808493","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808493","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140410839","display_name":"Xunzhuo Liu","orcid":"https://orcid.org/0009-0003-9156-5815"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I4210119657","display_name":"Semantic Designs (United States)","ror":"https://ror.org/025rxfw41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210119657"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Xunzhuo Liu","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada","vLLM Semantic Router Project, Remote, USA"],"raw_orcid":"https://orcid.org/0009-0003-9156-5815","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"vLLM Semantic Router Project, Remote, USA","institution_ids":["https://openalex.org/I4210119657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079956921","display_name":"Bowei He","orcid":"https://orcid.org/0000-0002-0360-2950"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Bowei He","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0360-2950","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372152","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0001-5252-3442"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I4210119657","display_name":"Semantic Designs (United States)","ror":"https://ror.org/025rxfw41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210119657"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Xue Liu","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada","vLLM Semantic Router Project, Remote, USA"],"raw_orcid":"https://orcid.org/0000-0001-5252-3442","affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates and McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"vLLM Semantic Router Project, Remote, USA","institution_ids":["https://openalex.org/I4210119657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140396874","display_name":"Haichen Zhang","orcid":"https://orcid.org/0009-0005-8977-5885"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haichen Zhang","raw_affiliation_strings":["AMD, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0009-0005-8977-5885","affiliations":[{"raw_affiliation_string":"AMD, Santa Clara, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140449800","display_name":"Huamin Chen","orcid":"https://orcid.org/0009-0007-0375-5686"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huamin Chen","raw_affiliation_strings":["Microsoft, Redmond, USA"],"raw_orcid":"https://orcid.org/0009-0007-0375-5686","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94520694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4753","last_page":"4757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.28060001134872437,"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":0.28060001134872437,"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":0.1290999948978424,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.07680000364780426,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5755000114440918},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5123999714851379},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5112000107765198},{"id":"https://openalex.org/keywords/functional-verification","display_name":"Functional verification","score":0.5012000203132629},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/runtime-verification","display_name":"Runtime verification","score":0.47679999470710754},{"id":"https://openalex.org/keywords/formal-verification","display_name":"Formal verification","score":0.4691999852657318},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44130000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968999743461609},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5755000114440918},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.5012000203132629},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C202973057","wikidata":"https://www.wikidata.org/wiki/Q7380130","display_name":"Runtime verification","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C3406870","wikidata":"https://www.wikidata.org/wiki/Q6044160","display_name":"Intelligent verification","level":5,"score":0.40130001306533813},{"id":"https://openalex.org/C33054407","wikidata":"https://www.wikidata.org/wiki/Q6504747","display_name":"Software verification","level":5,"score":0.36800000071525574},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C142284323","wikidata":"https://www.wikidata.org/wiki/Q7921323","display_name":"Verification","level":5,"score":0.29260000586509705},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2705000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808493","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808493","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2560647685","https://openalex.org/W2963963993","https://openalex.org/W3011411500","https://openalex.org/W3035030897","https://openalex.org/W3035038672","https://openalex.org/W3170490008","https://openalex.org/W4287888039","https://openalex.org/W4388979610","https://openalex.org/W4389519598","https://openalex.org/W4389520749","https://openalex.org/W4399932275","https://openalex.org/W4402671555","https://openalex.org/W4412886823","https://openalex.org/W4412887884","https://openalex.org/W7138434243"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"is":[3,33,146],"increasingly":[4],"deployed":[5],"in":[6,17,153],"enterprise":[7],"search":[8],"and":[9,19,46,59,96,105,117,125,156],"document-centric":[10],"assistants,":[11],"where":[12],"responses":[13,135],"must":[14],"be":[15],"grounded":[16],"long":[18,40],"complex":[20],"source":[21],"materials.":[22],"In":[23],"practice,":[24],"verifying":[25],"that":[26,81,127],"generated":[27],"answers":[28],"faithfully":[29],"reflect":[30],"retrieved":[31],"documents":[32,91],"difficult:":[34],"large":[35],"language":[36],"models":[37],"can":[38],"check":[39],"contexts":[41],"but":[42],"are":[43],"too":[44],"slow":[45],"costly":[47],"for":[48,168],"interactive":[49],"services,":[50],"while":[51],"lightweight":[52],"classifiers":[53],"operate":[54],"within":[55],"strict":[56],"context":[57],"limits":[58],"frequently":[60],"miss":[61],"evidence":[62],"outside":[63],"truncated":[64,138],"passages.":[65],"We":[66,110],"present":[67],"the":[68,112,123],"design":[69],"of":[70,133],"a":[71,77],"real-time":[72],"verification":[73,106,129,145],"component":[74],"integrated":[75],"into":[76],"production":[78],"RAG":[79],"pipeline":[80],"enables":[82],"full-document":[83],"grounding":[84],"under":[85],"latency":[86,158],"constraints.":[87],"The":[88],"system":[89],"processes":[90],"up":[92],"to":[93,101,121],"32K":[94],"tokens":[95],"employs":[97],"adaptive":[98],"inference":[99],"strategies":[100],"balance":[102],"response":[103],"time":[104],"coverage":[107],"across":[108],"workloads.":[109],"describe":[111],"architectural":[113],"decisions,":[114],"operational":[115],"trade-offs,":[116],"evaluation":[118],"methodology":[119],"used":[120],"deploy":[122],"verifier,":[124],"show":[126],"full-context":[128],"substantially":[130],"improves":[131],"detection":[132],"unsupported":[134],"compared":[136],"with":[137],"validation.":[139],"Our":[140],"experience":[141],"highlights":[142],"when":[143],"long-context":[144],"necessary,":[147],"why":[148],"chunk-based":[149],"checking":[150],"often":[151],"fails":[152],"real":[154],"documents,":[155],"how":[157],"budgets":[159],"shape":[160],"model":[161],"design.":[162],"These":[163],"findings":[164],"provide":[165],"practical":[166],"guidance":[167],"practitioners":[169],"building":[170],"reliable":[171],"large-scale":[172],"retrieval-augmented":[173],"applications.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}