{"id":"https://openalex.org/W4417336978","doi":"https://doi.org/10.1109/access.2025.3644595","title":"From Retrieval to Response: Tracing the Impact of Embedding Quality in RAG Systems","display_name":"From Retrieval to Response: Tracing the Impact of Embedding Quality in RAG Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417336978","doi":"https://doi.org/10.1109/access.2025.3644595"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3644595","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3644595","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3644595","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027277486","display_name":"Orlando Amaral","orcid":"https://orcid.org/0000-0001-5140-6439"},"institutions":[{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Orlando Amaral Cejas","raw_affiliation_strings":["Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-5140-6439","affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I4210112527"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023978917","display_name":"Yuejun Guo","orcid":"https://orcid.org/0000-0002-5535-2420"},"institutions":[{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Yuejun Guo","raw_affiliation_strings":["Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-5535-2420","affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I4210112527"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077863367","display_name":"Qiang Tang","orcid":"https://orcid.org/0000-0002-6153-4255"},"institutions":[{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Qiang Tang","raw_affiliation_strings":["Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-6153-4255","affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I4210112527"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93845028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"212773","last_page":"212781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8712000250816345,"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":0.8712000250816345,"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":0.03550000116229057,"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":0.019300000742077827,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8353000283241272},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7121999859809875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6159999966621399},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6098999977111816},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.529699981212616},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.3856000006198883}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8353000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823199987411499},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7121999859809875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6159999966621399},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3644595","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3644595","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3644595","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3644595","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2896457183","https://openalex.org/W2969545244","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3099700870","https://openalex.org/W3157758108","https://openalex.org/W4230431394","https://openalex.org/W4313547549","https://openalex.org/W4400307907","https://openalex.org/W4400943924","https://openalex.org/W4401857375","https://openalex.org/W4402667059","https://openalex.org/W4410340819","https://openalex.org/W4412480620","https://openalex.org/W4413640502","https://openalex.org/W4415798129"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Retrieval":[1],"Augmented":[2],"Generation":[3],"(RAG)":[4],"has":[5,76],"emerged":[6],"as":[7,57,89,188],"a":[8,128,139,144,173,202,222],"powerful":[9],"paradigm":[10],"for":[11,93,155],"enhancing":[12],"the":[13,68,90,98,101,115,121,160,167,191],"capability":[14],"of":[15,100,117,124,132,207],"Large":[16],"Language":[17],"Models":[18],"(LLMs)":[19],"by":[20],"incorporating":[21],"external,":[22],"up-to-date,":[23],"or":[24],"domain-specific":[25],"information":[26],"through":[27],"retrieval":[28,95,152,178],"mechanisms.":[29],"In":[30],"their":[31,64],"implementation,":[32],"RAG":[33,74,181,208],"systems":[34],"usually":[35],"rely":[36],"on":[37,120,163,221],"vector":[38],"embedding":[39,71,118,199],"to":[40,63,211],"identify":[41],"relevant":[42],"context":[43],"from":[44],"an":[45],"underlying":[46],"knowledge":[47],"base,":[48],"and":[49,60,73,97,143,180,215],"have":[50],"gained":[51],"widespread":[52],"adoption":[53],"across":[54],"tasks":[55],"such":[56],"question":[58],"answering":[59],"summarization":[61],"due":[62],"superior":[65],"performance.":[66],"Surprisingly,":[67],"interplay":[69],"between":[70,177],"quality":[72,119,200],"performance":[75,123,130],"not":[77,187],"received":[78],"much":[79],"attention":[80],"so":[81],"far,":[82],"even":[83],"though":[84],"it":[85,216],"is":[86,172,186,201],"commonly":[87],"perceived":[88],"key":[91],"factor":[92],"influencing":[94],"accuracy":[96,153,179],"trustworthiness":[99],"generated":[102],"answer.":[103],"To":[104],"fill":[105],"in":[106,109,190],"this":[107,110,184],"gap,":[108],"paper,":[111],"we":[112,148],"systematically":[113],"investigate":[114],"impact":[116],"overall":[122],"RAG-based":[125],"applications.":[126],"Through":[127],"comprehensive":[129],"evaluation":[131],"12":[133],"embeddings":[134],"over":[135],"two":[136],"datasets":[137],"(i.e.,":[138],"public":[140,168],"dataset":[141,169],"SQuAD":[142],"private":[145,192],"Telecom":[146,193],"dataset),":[147],"reveal":[149],"quite":[150],"different":[151],"levels":[154],"these":[156],"embeddings,":[157],"while":[158,183],"following":[159],"same":[161],"trend":[162],"both":[164],"datasets.":[165],"For":[166],"SQuAD,":[170],"there":[171],"strong":[174,189],"positive":[175],"correlation":[176],"performance,":[182],"relationship":[185],"dataset.":[194],"Our":[195],"findings":[196],"highlight":[197],"that":[198],"fundamental":[203],"yet":[204],"tricky":[205],"determinant":[206],"systems\u2019":[209],"ability":[210],"generate":[212],"trustworthy":[213],"responses":[214],"should":[217],"be":[218],"examined":[219],"deeply":[220],"case-by-case":[223],"basis.":[224],"We":[225],"open":[226],"source":[227],"our":[228],"full":[229],"implementation":[230],"at:":[231],"https://github.com/Yuejun-GUO/RAG-exp.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-15T00:00:00"}