{"id":"https://openalex.org/W7147658870","doi":"https://doi.org/10.48550/arxiv.2603.26670","title":"SRAG: RAG with Structured Data Improves Vector Retrieval","display_name":"SRAG: RAG with Structured Data Improves Vector Retrieval","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7147658870","doi":"https://doi.org/10.48550/arxiv.2603.26670"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26670","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041467219","display_name":"Shalin Shah","orcid":"https://orcid.org/0000-0002-3770-1391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Shalin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132676580","display_name":"Srikanth Ryali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryali, Srikanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027912683","display_name":"Ramasubbu Venkatesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venkatesh, Ramasubbu","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5584999918937683,"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":0.5584999918937683,"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":0.3301999866962433,"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":0.040300000458955765,"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/graph","display_name":"Graph","score":0.5551999807357788},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.43470001220703125},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.39730000495910645},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.3885999917984009},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.38769999146461487},{"id":"https://openalex.org/keywords/boolean-conjunctive-query","display_name":"Boolean conjunctive query","score":0.349700003862381},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.34869998693466187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211999893188477},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38769999146461487},{"id":"https://openalex.org/C24755975","wikidata":"https://www.wikidata.org/wiki/Q4943354","display_name":"Boolean conjunctive query","level":5,"score":0.349700003862381},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26670","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26670","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval":[0],"Augmented":[1],"Generation":[2],"(RAG)":[3],"provides":[4],"the":[5,12,43,55,63,68,71,92,95,120,131,134],"necessary":[6],"informational":[7],"grounding":[8],"to":[9,39,86,137],"LLMs":[10],"in":[11,94,139,156,191],"form":[13,96],"of":[14,35,59,67,97],"chunks":[15,93],"retrieved":[16],"from":[17],"a":[18,33,52,87,140],"vector":[19,65],"database":[20],"or":[21],"through":[22],"web":[23],"search.":[24],"RAG":[25,60,80],"could":[26],"also":[27],"use":[28],"knowledge":[29,107],"graph":[30,108],"triples":[31,109],"as":[32,89,91,125],"means":[34],"providing":[36],"factual":[37],"information":[38,85],"an":[40,126],"LLM.":[41],"However,":[42],"retrieval":[44,121],"is":[45,155],"only":[46],"based":[47],"on":[48,62],"representational":[49],"similarity":[50],"between":[51],"question":[53,141],"and":[54,70,101,110,159,172],"contents.":[56],"The":[57,152,162],"performance":[58],"depends":[61],"numeric":[64],"representations":[66],"query":[69,88,100],"chunks.":[72],"To":[73],"improve":[74],"these":[75],"representations,":[76],"we":[77],"propose":[78],"Structured":[79],"(SRAG),":[81],"which":[82],"adds":[83],"structured":[84],"well":[90],"topics,":[98],"sentiments,":[99],"chunk":[102],"types":[103],"(e.g.,":[104],"informational,":[105],"quantitative),":[106],"semantic":[111],"tags.":[112],"Experiments":[113],"indicate":[114],"that":[115,130,165,179],"this":[116],"method":[117,132,167],"significantly":[118],"improves":[119,133],"process.":[122],"Using":[123],"GPT-5":[124],"LLM-as-a-judge,":[127],"results":[128,163],"show":[129],"score":[135],"given":[136],"answers":[138],"answering":[142],"system":[143],"by":[144],"30%":[145],"(p-value":[146],"=":[147],"2e-13)":[148],"(with":[149],"tighter":[150],"bounds).":[151],"strongest":[153],"improvement":[154],"comparative,":[157],"analytical":[158],"predictive":[160],"questions.":[161],"suggest":[164],"our":[166],"enables":[168],"broader,":[169],"more":[170,185],"diverse,":[171],"episodic-style":[173],"retrieval.":[174],"Tail":[175],"risk":[176],"analysis":[177],"shows":[178],"SRAG":[180],"attains":[181],"very":[182],"large":[183],"gains":[184],"often,":[186],"with":[187],"losses":[188],"remaining":[189],"minor":[190],"magnitude.":[192]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-02T00:00:00"}