{"id":"https://openalex.org/W7147217740","doi":"https://doi.org/10.1109/cnml68938.2026.11452538","title":"A Multi-Scale Adaptive Retrieval-Augmented Generation Framework with Semantic and Structural Knowledge Graphs","display_name":"A Multi-Scale Adaptive Retrieval-Augmented Generation Framework with Semantic and Structural Knowledge Graphs","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147217740","doi":"https://doi.org/10.1109/cnml68938.2026.11452538"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103245987","display_name":"F. L. Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I34155123","display_name":"Hebei University of Science and Technology","ror":"https://ror.org/05h3pkk68","country_code":"CN","type":"education","lineage":["https://openalex.org/I34155123"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fuhan Ning","raw_affiliation_strings":["Hebei University of Science and Technology,School of Information Science and Engineering,Shjjiazhuang,China"],"affiliations":[{"raw_affiliation_string":"Hebei University of Science and Technology,School of Information Science and Engineering,Shjjiazhuang,China","institution_ids":["https://openalex.org/I34155123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132685712","display_name":"Yu Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I34155123","display_name":"Hebei University of Science and Technology","ror":"https://ror.org/05h3pkk68","country_code":"CN","type":"education","lineage":["https://openalex.org/I34155123"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Bai","raw_affiliation_strings":["Hebei University of Science and Technology,School of Information Science and Engineering,Shjjiazhuang,China"],"affiliations":[{"raw_affiliation_string":"Hebei University of Science and Technology,School of Information Science and Engineering,Shjjiazhuang,China","institution_ids":["https://openalex.org/I34155123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103245987"],"corresponding_institution_ids":["https://openalex.org/I34155123"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93891046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1041","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8758999705314636,"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":0.8758999705314636,"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":0.05649999901652336,"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":0.011599999852478504,"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/graph","display_name":"Graph","score":0.508400022983551},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45660001039505005},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.43650001287460327},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4050999879837036},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.40459999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159000277519226},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45660001039505005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4505000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C234837","wikidata":"https://www.wikidata.org/wiki/Q1420493","display_name":"Conceptual graph","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5888331532478333,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W4404783159","https://openalex.org/W4404835216","https://openalex.org/W4411119292"],"related_works":[],"abstract_inverted_index":{"The":[0,152,183],"combination":[1],"of":[2,39,62,78,164,180,216],"large":[3],"language":[4],"models":[5,156],"and":[6,18,57,74,106,122,143,148,158,166,209],"retrieval":[7,47,207],"augmented":[8],"generation":[9,116,211],"(RAG)":[10],"demonstrates":[11],"great":[12],"potential":[13],"in":[14,45,88,99,161,205,220],"complex":[15,100,221],"multi-hop":[16,104,222],"reasoning":[17,105],"long":[19,51],"document":[20],"question":[21,90,223],"answering":[22,91,224],"tasks.":[23,225],"However,":[24],"the":[25,37,41,46,60,76,79,83,129,162,178,187,194,214,217],"existing":[26,84,195],"RAG":[27,197],"methods":[28,85],"still":[29,97],"face":[30],"two":[31],"key":[32,63],"challenges:":[33],"Firstly,":[34],"there":[35],"is":[36,96,133],"issue":[38],"determining":[40],"appropriate":[42],"context":[43,52,69,150],"range":[44],"stage.":[48],"An":[49],"overly":[50,67],"may":[53,70],"introduce":[54],"redundant":[55],"information":[56],"interfere":[58],"with":[59,193],"modeling":[61],"information,":[64],"while":[65],"an":[66],"short":[68],"miss":[71],"important":[72],"facts":[73],"affect":[75],"accuracy":[77],"generated":[80],"results.":[81],"Secondly,":[82],"perform":[86],"well":[87],"single-fact":[89],"tasks,":[92],"but":[93],"their":[94,159],"performance":[95],"limited":[98],"scenarios":[101],"such":[102,139],"as":[103,140],"cross-paragraph":[107],"evidence":[108,181],"integration.This":[109],"paper":[110],"proposes":[111],"a":[112],"multi-scale":[113],"adaptive":[114],"retrieval-enhanced":[115],"framework":[117],"based":[118],"on":[119,186],"both":[120,206],"semantic":[121,153,172],"structural":[123,130],"knowledge":[124,131,154],"graphs.":[125],"In":[126],"this":[127],"framework,":[128],"graph":[132,155],"centered":[134],"around":[135],"different":[136],"granularity":[137],"levels":[138],"chapters,":[141],"paragraphs,":[142,175],"sentences,":[144],"to":[145,170],"support":[146],"flexible":[147],"adjustable":[149],"slicing.":[151],"entities":[157],"relationships":[160],"form":[163],"triples,":[165],"uses":[167],"entity":[168],"cross-connections":[169],"achieve":[171],"associations":[173],"across":[174],"effectively":[176],"enhancing":[177],"completeness":[179],"retrieval.":[182],"experimental":[184],"results":[185],"HotpotQA":[188],"dataset":[189],"show":[190],"that,":[191],"compared":[192],"mainstream":[196],"methods,":[198],"our":[199],"method":[200,219],"has":[201],"achieved":[202],"stable":[203],"improvements":[204],"quality":[208],"answer":[210],"quality,":[212],"verifying":[213],"effectiveness":[215],"proposed":[218]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}