{"id":"https://openalex.org/W4415970074","doi":"https://doi.org/10.1109/cist65886.2025.11224301","title":"ARCADIA: A Scalable Arabic RAG Framework with Hierarchical and Context-Aware Retrieval","display_name":"ARCADIA: A Scalable Arabic RAG Framework with Hierarchical and Context-Aware Retrieval","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4415970074","doi":"https://doi.org/10.1109/cist65886.2025.11224301"},"language":null,"primary_location":{"id":"doi:10.1109/cist65886.2025.11224301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist65886.2025.11224301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th Congress on Information Science and Technology (CiSt)","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/A5115894620","display_name":"Mitha Alshammary","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mitha Alshammary","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018053852","display_name":"Md Nahiyan Uddin","orcid":"https://orcid.org/0009-0007-3778-5955"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Nahiyan Uddin","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005002693","display_name":"Latifur Khan","orcid":"https://orcid.org/0000-0002-9300-1576"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Latifur Khan","raw_affiliation_strings":["The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Computer Science,Richardson,TX,USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115894620"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18152423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"238","last_page":"243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6322000026702881,"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":0.6322000026702881,"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":0.05999999865889549,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.04879999905824661,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8763999938964844},{"id":"https://openalex.org/keywords/arcadia","display_name":"Arcadia","score":0.5831000208854675},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4277999997138977},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8763999938964844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133999705314636},{"id":"https://openalex.org/C2776946774","wikidata":"https://www.wikidata.org/wiki/Q4785125","display_name":"Arcadia","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cist65886.2025.11224301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist65886.2025.11224301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th Congress on Information Science and Technology (CiSt)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4406417785"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"and":[4,45,53,64,91,102],"standard":[5],"Retrieval-Augmented":[6],"Generation":[7],"(RAG)":[8],"frameworks":[9],"often":[10],"struggle":[11],"to":[12],"handle":[13],"large-scale":[14],"data,":[15],"especially":[16],"in":[17],"low-resource":[18],"languages":[19],"like":[20],"Arabic.":[21],"This":[22],"paper":[23],"introduces":[24],"ARCADIA,":[25],"a":[26,37,70,79],"novel":[27],"scalable":[28],"RAG":[29],"framework":[30],"that":[31],"overcomes":[32],"these":[33],"scalability":[34,101],"challenges":[35],"through":[36],"hierarchical":[38],"retrieval":[39,52],"mechanism,":[40],"an":[41],"integrated":[42],"noise":[43],"filter,":[44],"optimized":[46],"prompt":[47],"engineering.":[48],"By":[49],"leveraging":[50],"multi-level":[51],"distributed":[54],"indexing,":[55],"ARCADIA":[56,82],"efficiently":[57],"processes":[58],"massive":[59],"datasets,":[60],"ensuring":[61],"contextually":[62],"accurate":[63],"factually":[65],"grounded":[66],"responses.":[67],"Evaluated":[68],"on":[69],"question-answering":[71],"task":[72],"using":[73],"over":[74],"2,800":[75],"Arabic":[76],"books":[77],"by":[78],"domain":[80],"expert,":[81],"significantly":[83],"outperforms":[84],"state-of-the-art":[85],"LLMs":[86],"such":[87],"as":[88],"GPT-4,":[89],"GPT-4o,":[90],"GPT-4o-mini,":[92],"achieving":[93],"high":[94],"accuracy":[95],"of":[96],"98.5%":[97],"while":[98],"maintaining":[99],"exceptional":[100],"robustness.":[103]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-06T00:00:00"}