{"id":"https://openalex.org/W4417097942","doi":"https://doi.org/10.48550/arxiv.2506.06339","title":"Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components","display_name":"Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W4417097942","doi":"https://doi.org/10.48550/arxiv.2506.06339"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.06339","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06339","pdf_url":"https://arxiv.org/pdf/2506.06339","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/2506.06339","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073144243","display_name":"Jumana Alsubhi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alsubhi, Jumana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072138648","display_name":"Mohammad D. Alahmadi","orcid":"https://orcid.org/0000-0002-3399-2996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alahmadi, Mohammad D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697063","display_name":"Ahmed Alhusayni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alhusayni, Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697064","display_name":"Ibrahim Aldailami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aldailami, Ibrahim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697065","display_name":"Israa Hamdine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamdine, Israa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697066","display_name":"Ahmad Shabana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shabana, Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120697067","display_name":"Yazeed Iskandar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iskandar, Yazeed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120697068","display_name":"Suhayb Khayyat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khayyat, Suhayb","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.6847000122070312,"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":0.6847000122070312,"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":0.12800000607967377,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.05420000106096268,"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/chunking","display_name":"Chunking (psychology)","score":0.7046999931335449},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6029999852180481},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5656999945640564},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4569999873638153},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200999855995178},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.7046999931335449},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5066999793052673},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46869999170303345},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26649999618530273}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.06339","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06339","pdf_url":"https://arxiv.org/pdf/2506.06339","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.06339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06339","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.06339","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06339","pdf_url":"https://arxiv.org/pdf/2506.06339","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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],"Generation":[1],"(RAG)":[2],"has":[3],"emerged":[4],"as":[5,104],"a":[6,45,61,113],"powerful":[7],"architecture":[8],"for":[9,30,38,134,144],"combining":[10],"the":[11,17,33,68,105],"precision":[12],"of":[13,19,35,49,64,112],"retrieval":[14],"systems":[15],"with":[16],"fluency":[18],"large":[20],"language":[21,59],"models.":[22,109],"While":[23],"several":[24],"studies":[25],"have":[26],"investigated":[27],"RAG":[28,36,51,138],"pipelines":[29,139],"high-resource":[31],"languages,":[32],"optimization":[34],"components":[37,147],"Arabic":[39,65,137],"remains":[40],"underexplored.":[41],"This":[42],"study":[43],"presents":[44],"comprehensive":[46],"empirical":[47],"evaluation":[48],"state-of-the-art":[50],"components-including":[52],"chunking":[53,93],"strategies,":[54],"embedding":[55,108],"models,":[56],"rerankers,":[57],"and":[58,85,101,122,140],"models-across":[60],"diverse":[62],"set":[63],"datasets.":[66],"Using":[67],"RAGAS":[69],"framework,":[70],"we":[71],"systematically":[72],"compare":[73],"performance":[74],"across":[75,148],"four":[76],"core":[77],"metrics:":[78],"context":[79,81],"precision,":[80],"recall,":[82],"answer":[83,86],"faithfulness,":[84],"relevancy.":[87],"Our":[88],"experiments":[89],"demonstrate":[90],"that":[91],"sentence-aware":[92],"outperforms":[94],"all":[95],"other":[96],"segmentation":[97],"methods,":[98],"while":[99],"BGE-M3":[100],"Multilingual-E5-large":[102],"emerge":[103],"most":[106],"effective":[107],"The":[110],"inclusion":[111],"reranker":[114],"(bge-reranker-v2-m3)":[115],"significantly":[116],"boosts":[117],"faithfulness":[118],"in":[119,126],"complex":[120],"datasets,":[121],"Aya-8B":[123],"surpasses":[124],"StableLM":[125],"generation":[127],"quality.":[128],"These":[129],"findings":[130],"provide":[131],"critical":[132],"insights":[133],"building":[135],"high-quality":[136],"offer":[141],"practical":[142],"guidelines":[143],"selecting":[145],"optimal":[146],"different":[149],"document":[150],"types.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}