{"id":"https://openalex.org/W4417100168","doi":"https://doi.org/10.48550/arxiv.2510.10114","title":"LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora","display_name":"LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora","publication_year":2025,"publication_date":"2025-10-11","ids":{"openalex":"https://openalex.org/W4417100168","doi":"https://doi.org/10.48550/arxiv.2510.10114"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.10114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10114","pdf_url":"https://arxiv.org/pdf/2510.10114","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.10114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuang, Luyao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Luyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004805571","display_name":"Shengyuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shengyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595167","display_name":"Yilin Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049663232","display_name":"Huachi Zhou","orcid":"https://orcid.org/0000-0002-8301-8470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Huachi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592591","display_name":"Yujing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yujing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353471","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0001-5902-1824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058417704","display_name":"Qinggang Zhang","orcid":"https://orcid.org/0000-0002-0247-4942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qinggang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055037545","display_name":"Xiao Huang","orcid":"https://orcid.org/0000-0002-3867-900X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiao","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":0.48649999499320984,"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":0.48649999499320984,"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":0.3790999948978424,"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":0.026599999517202377,"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/relationship-extraction","display_name":"Relationship extraction","score":0.6229000091552734},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5522000193595886},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5157999992370605},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5139999985694885},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4778999984264374},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3312999904155731},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3301999866962433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263999819755554},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6229000091552734},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.10114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10114","pdf_url":"https://arxiv.org/pdf/2510.10114","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.10114","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.10114","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.10114","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10114","pdf_url":"https://arxiv.org/pdf/2510.10114","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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-Augmented":[0,98],"Generation":[1],"(RAG)":[2],"is":[3,33],"widely":[4],"used":[5],"to":[6,40],"mitigate":[7],"hallucinations":[8],"of":[9,89,136,156],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"by":[14,176],"leveraging":[15],"external":[16],"knowledge.":[17],"While":[18],"effective":[19],"for":[20,48,66],"simple":[21],"queries,":[22],"traditional":[23],"RAG":[24,56],"systems":[25,92],"struggle":[26],"with":[27,73,141],"large-scale,":[28],"unstructured":[29],"corpora":[30],"where":[31],"information":[32],"fragmented.":[34],"Recent":[35],"advances":[36],"incorporate":[37],"knowledge":[38],"graphs":[39,72],"capture":[41],"relational":[42],"structures,":[43],"enabling":[44],"more":[45],"comprehensive":[46],"retrieval":[47,80,179],"complex,":[49],"multi-hop":[50],"reasoning":[51],"tasks.":[52],"However,":[53],"existing":[54,90],"graph-based":[55],"(GraphRAG)":[57],"methods":[58],"rely":[59],"on":[60,186],"unstable":[61,130],"and":[62,93,108,126,144,153,198],"costly":[63],"relation":[64,131],"extraction":[65,125],"graph":[67,106,137],"construction,":[68],"often":[69],"producing":[70],"noisy":[71],"incorrect":[74],"or":[75],"inconsistent":[76],"relations":[77],"that":[78,103,190],"degrade":[79],"quality.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"revisit":[86],"the":[87,157],"pipeline":[88],"GraphRAG":[91],"propose":[94],"LinearRAG":[95,113,162,191],"(Linear":[96],"Graph-based":[97],"Generation),":[99],"an":[100,151],"efficient":[101],"framework":[102],"enables":[104],"reliable":[105,154],"construction":[107,138],"precise":[109],"passage":[110,178],"retrieval.":[111],"Specifically,":[112],"constructs":[114],"a":[115,164],"relation-free":[116],"hierarchical":[117],"graph,":[118],"termed":[119],"Tri-Graph,":[120],"using":[121],"only":[122],"lightweight":[123],"entity":[124,169],"semantic":[127,173],"linking,":[128],"avoiding":[129],"modeling.":[132],"This":[133],"new":[134],"paradigm":[135],"scales":[139],"linearly":[140],"corpus":[142],"size":[143],"incurs":[145],"no":[146],"extra":[147],"token":[148],"consumption,":[149],"providing":[150],"economical":[152],"indexing":[155],"original":[158],"passages.":[159],"For":[160],"retrieval,":[161],"adopts":[163],"two-stage":[165],"strategy:":[166],"(i)":[167],"relevant":[168],"activation":[170],"via":[171],"local":[172],"bridging,":[174],"followed":[175],"(ii)":[177],"through":[180],"global":[181],"importance":[182],"aggregation.":[183],"Extensive":[184],"experiments":[185],"four":[187],"datasets":[188,199],"demonstrate":[189],"significantly":[192],"outperforms":[193],"baseline":[194],"models.":[195],"Our":[196],"code":[197],"are":[200],"available":[201],"at":[202],"https://github.com/DEEP-PolyU/LinearRAG.":[203]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-15T00:00:00"}