{"id":"https://openalex.org/W4416798136","doi":"https://doi.org/10.1109/access.2025.3638761","title":"Neural-Symbolic Dual-Indexing Architectures for Scalable Retrieval-Augmented Generation","display_name":"Neural-Symbolic Dual-Indexing Architectures for Scalable Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416798136","doi":"https://doi.org/10.1109/access.2025.3638761"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3638761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3638761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072346729","display_name":"Jie-Si Yang","orcid":"https://orcid.org/0000-0002-9826-4252"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jie-Si Yang","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA","University of Utah, Salt Lake City, USA"],"raw_orcid":"https://orcid.org/0000-0002-9826-4252","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah, Salt Lake City, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082751082","display_name":"Zhuoqi Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoqi Zeng","raw_affiliation_strings":["New York University, New York, NY, USA","New York University, New York, USA"],"raw_orcid":"https://orcid.org/0009-0007-9499-7735","affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zijian Shen","orcid":"https://orcid.org/0009-0001-1157-6510"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Shen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0001-1157-6510","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072346729"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":8.3104,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97400187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"210507","last_page":"210519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6342999935150146,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6342999935150146,"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":0.10260000079870224,"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":0.07460000365972519,"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/scalability","display_name":"Scalability","score":0.5942999720573425},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.511900007724762},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4090000092983246},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3865000009536743},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.33550000190734863},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.2906999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864799976348877},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46860000491142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4090000092983246},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C4969071","wikidata":"https://www.wikidata.org/wiki/Q7316353","display_name":"Result set","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3638761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ded342a88ba042d5b8de379ec1810976","is_oa":true,"landing_page_url":"https://doaj.org/article/ded342a88ba042d5b8de379ec1810976","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 210507-210519 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3638761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contemporary":[0],"retrieval-augmented":[1],"generation":[2,140],"systems":[3],"face":[4],"a":[5,21,63,202],"fundamental":[6],"trade-off":[7],"between":[8],"semantic":[9,52,207],"comprehensiveness":[10],"and":[11,78,144],"computational":[12],"tractability":[13],"when":[14],"scaling":[15],"to":[16,133,156],"billion-token":[17],"corpora.":[18],"We":[19],"present":[20],"unified":[22],"framework":[23,190],"that":[24,112,183],"reconciles":[25],"this":[26,57],"tension":[27],"through":[28,164,179],"<italic":[29],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[30],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">neural-symbolic":[31],"dual-indexing</i>,":[32],"wherein":[33],"sparse":[34],"graph":[35,136],"skeletons":[36],"constructed":[37],"from":[38,116],"high-centrality":[39],"document":[40],"chunks":[41],"enable":[42],"structured":[43,210],"reasoning,":[44],"while":[45,100,138],"complementary":[46],"bipartite":[47],"keyword":[48],"indices":[49],"ensure":[50],"broad":[51],"coverage.":[53],"Our":[54],"architecture":[55,196],"achieves":[56],"decomposition":[58],"by":[59,142,147,186],"formulating":[60],"retrieval":[61,145,170,199],"as":[62,193],"constrained":[64],"optimization":[65],"problem":[66],"over":[67],"heterogeneous":[68],"index":[69],"structures,":[70],"employing":[71],"Prize-Collecting":[72],"Steiner":[73],"Trees":[74],"for":[75,81,197,205],"subgraph":[76],"extraction":[77],"Personalized":[79],"PageRank":[80],"multi-hop":[82,161],"traversal.":[83],"Through":[84],"synergistic":[85],"integration":[86],"of":[87,120],"Graph":[88],"Neural":[89],"Networks":[90],"with":[91],"vector":[92],"embeddings,":[93],"the":[94,117,194],"system":[95],"performs":[96],"explicit":[97],"relational":[98],"reasoning":[99,211],"maintaining":[101],"sub-second":[102],"query":[103],"latency.":[104],"Empirical":[105],"evaluation":[106],"across":[107],"6.0":[108],"benchmark":[109],"datasets":[110],"demonstrates":[111],"selective":[113],"skeleton":[114],"construction":[115,137],"top":[118],"20.0%":[119],"chunks\u2014identified":[121],"via":[122],"eigenvector":[123],"centrality":[124],"on":[125,160],"k-nearest":[126],"neighbor":[127],"graphs\u2014yields":[128],"10.0\u00d7":[129],"cost":[130],"reduction":[131],"relative":[132],"exhaustive":[134],"knowledge":[135],"improving":[139],"quality":[141],"32.4%":[143],"coverage":[146],"92.4%.":[148],"Furthermore,":[149],"neural-symbolic":[150],"coupling":[151],"enables":[152],"7.0-billion":[153],"parameter":[154],"models":[155],"match":[157],"GPT-4":[158],"performance":[159],"question":[162],"answering":[163],"single-step":[165],"graph-guided":[166],"inference,":[167],"eliminating":[168],"iterative":[169],"overhead.":[171],"Production":[172],"deployments":[173],"validate":[174],"sub-200.0ms":[175],"latency":[176],"at":[177],"scale":[178],"hierarchical":[180],"caching":[181],"strategies":[182],"reduce":[184],"time-to-first-token":[185],"4.0\u00d7.":[187],"The":[188],"proposed":[189],"establishes":[191],"dual-indexing":[192],"canonical":[195],"enterprise":[198],"systems,":[200],"providing":[201],"principled":[203],"methodology":[204],"balancing":[206],"understanding":[208],"against":[209],"in":[212],"large-scale":[213],"information":[214],"access.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-11-28T00:00:00"}