{"id":"https://openalex.org/W7156676003","doi":"https://doi.org/10.48550/arxiv.2604.22843","title":"Structure Guided Retrieval-Augmented Generation for Factual Queries","display_name":"Structure Guided Retrieval-Augmented Generation for Factual Queries","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7156676003","doi":"https://doi.org/10.48550/arxiv.2604.22843"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22843","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.2604.22843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134758090","display_name":"Miao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134808226","display_name":"xiao qin zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134797270","display_name":"Yi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077602137","display_name":"Chunli Lv","orcid":"https://orcid.org/0000-0002-2005-6488"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Chunli","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":0.6934999823570251,"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":0.6934999823570251,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09120000153779984,"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":0.06109999865293503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5511000156402588},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41589999198913574},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3862000107765198},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3659999966621399},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652000188827515},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4535999894142151},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3862000107765198},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C24755975","wikidata":"https://www.wikidata.org/wiki/Q4943354","display_name":"Boolean conjunctive query","level":5,"score":0.296099990606308},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22843","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.2604.22843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22843","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/4","display_name":"Quality Education","score":0.41329333186149597}],"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":[0,109],"Generation":[1,110],"(RAG)":[2],"has":[3],"been":[4],"proposed":[5],"to":[6,35,40,56,96,129,133,190],"mitigate":[7],"hallucinations":[8],"in":[9],"large":[10],"language":[11],"models":[12,113],"(LLMs),":[13],"where":[14],"generated":[15,43],"outputs":[16],"may":[17],"be":[18],"factually":[19],"incorrect.":[20],"However,":[21],"existing":[22],"RAG":[23,92],"approaches":[24],"predominantly":[25],"rely":[26],"on":[27,183],"vector":[28],"similarity":[29],"for":[30,93],"retrieval,":[31],"which":[32,112],"is":[33,81],"prone":[34],"semantic":[36],"noise":[37],"and":[38,123,149],"fails":[39],"ensure":[41],"that":[42,86,136,177],"responses":[44],"fully":[45],"satisfy":[46,97],"the":[47,75,82,114,125,131],"complex":[48,167],"conditions":[49],"specified":[50,139],"by":[51],"factual":[52,94],"queries,":[53],"often":[54],"leading":[55],"incorrect":[57],"answers.":[58],"To":[59,74,142],"address":[60],"this":[61,80,102],"challenge,":[62],"we":[63,105,147],"introduce":[64],"a":[65,157],"novel":[66,103],"research":[67],"problem,":[68,104],"named":[69],"Exact":[70,152],"Retrieval":[71,153],"Problem":[72],"(ERP).":[73],"best":[76],"of":[77,145],"our":[78],"knowledge,":[79],"first":[83],"problem":[84],"formulation":[85],"explicitly":[87],"incorporates":[88],"structural":[89],"information":[90],"into":[91],"questions":[95],"all":[98,138,194],"query":[99,140],"conditions.":[100,141],"For":[101],"propose":[106],"Structure":[107],"Guided":[108],"(SG-RAG),":[111],"retrieval":[115],"process":[116],"as":[117],"an":[118],"embedding-based":[119],"subgraph":[120],"matching":[121],"task,":[122],"uses":[124],"retrieved":[126],"topological":[127],"structures":[128],"guide":[130],"LLM":[132],"generate":[134],"answers":[135],"meet":[137],"facilitate":[143],"evaluation":[144,195],"ERP,":[146],"construct":[148],"publicly":[150],"release":[151],"Question":[154],"Answering":[155],"(ERQA),":[156],"large-scale":[158],"dataset":[159],"comprising":[160],"120000":[161],"fact-oriented":[162],"QA":[163],"pairs,":[164],"each":[165],"involving":[166],"conditions,":[168],"spanning":[169],"20":[170],"diverse":[171],"domains.":[172],"The":[173],"experimental":[174],"results":[175],"demonstrate":[176],"SG-RAG":[178],"significantly":[179],"outperforms":[180],"strong":[181],"baselines":[182],"ERQA,":[184],"delivering":[185],"absolute":[186],"improvements":[187],"from":[188],"20.68":[189],"50.88":[191],"points":[192],"across":[193],"metrics,":[196],"while":[197],"maintaining":[198],"reasonable":[199],"computational":[200],"overhead.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}