{"id":"https://openalex.org/W4416034051","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.769","title":"pFedRAG: A Personalized Federated Retrieval-Augmented Generation System with Depth-Adaptive Tiered Embedding Tuning","display_name":"pFedRAG: A Personalized Federated Retrieval-Augmented Generation System with Depth-Adaptive Tiered Embedding Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034051","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.769"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.769","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.769","pdf_url":"https://aclanthology.org/2025.findings-emnlp.769.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.769.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032638226","display_name":"Hui He","orcid":"https://orcid.org/0000-0002-4144-5124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hangyu He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020561518","display_name":"Kai Wu","orcid":"https://orcid.org/0000-0002-7057-0442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008974159","display_name":"Ren Ping Liu","orcid":"https://orcid.org/0000-0001-7001-6305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren Ping Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544825","display_name":"Wei Ni","orcid":"https://orcid.org/0000-0002-4933-594X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43270069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14255","last_page":"14268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.1103999987244606,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.1103999987244606,"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/T11269","display_name":"Algorithms and Data Compression","score":0.10909999907016754,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.059300001710653305,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/embedding","display_name":"Embedding","score":0.5447999835014343},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.30000001192092896},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.2696000039577484},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.2524999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005000114440918},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23260000348091125},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23180000483989716}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.769","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.769","pdf_url":"https://aclanthology.org/2025.findings-emnlp.769.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:ro.ecu.edu.au:ecuworks2022-2026-8789","is_oa":true,"landing_page_url":"https://ro.ecu.edu.au/ecuworks2022-2026/7789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400464","display_name":"Research Online (Edith Cowan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12079687","host_organization_name":"Edith Cowan University","host_organization_lineage":["https://openalex.org/I12079687"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research outputs 2022 to 2026","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.769","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.769","pdf_url":"https://aclanthology.org/2025.findings-emnlp.769.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034051.pdf","grobid_xml":"https://content.openalex.org/works/W4416034051.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"can":[4,39],"undergo":[5],"hallucinations":[6],"in":[7],"specialized":[8],"domains,":[9],"and":[10,53,101,112,126,139,164],"standard":[11],"Retrieval-Augmented":[12],"Generation":[13],"(RAG)":[14],"often":[15],"falters":[16],"due":[17],"to":[18,42,74,97,143],"general-purpose":[19],"embeddings":[20],"ill-suited":[21],"for":[22,109],"domain-specific":[23,25],"terminology.Though":[24],"fine-tuning":[26,70],"enhances":[27],"retrieval,":[28],"centralizing":[29],"data":[30,49,56,111,162],"introduces":[31],"privacy":[32],"risks.The":[33],"use":[34],"of":[35,48,71,115,174],"federated":[36],"learning":[37],"(FL)":[38],"alleviate":[40],"this":[41],"some":[43],"extent,":[44],"but":[45],"faces":[46],"challenges":[47],"heterogeneity,":[50,163],"poor":[51],"personalization,":[52],"expensive":[54],"training":[55,113],"generation.We":[57],"propose":[58],"pFedRAG,":[59],"a":[60,81,90,102,131],"novel":[61],"Personalized":[62,103],"Federated":[63],"RAG":[64],"framework,":[65],"which":[66,88],"enables":[67],"efficient":[68],"collaborative":[69],"embedding":[72],"models":[73],"address":[75],"these":[76],"challenges.The":[77],"key":[78],"contribution":[79],"is":[80,119],"new":[82],"Depth-Adaptive":[83],"Tiered":[84],"Embedding":[85],"(DATE)":[86],"architecture,":[87],"comprises":[89],"Global":[91],"Shared":[92],"Layer,":[93],"combined":[94],"using":[95],"FL":[96],"capture":[98],"common":[99],"knowledge,":[100],"Layer":[104],"with":[105],"adjustable":[106],"depth":[107,118],"tailored":[108],"local":[110,136],"results":[114],"each":[116],"client.The":[117],"locally":[120],"controlled":[121],"based":[122],"on":[123,148],"crafted":[124],"metrics":[125],"scoring":[127],"criteria.Also,":[128],"pFedRAG":[129,156],"incorporates":[130],"fully":[132],"client-side":[133],"pipeline":[134],"leveraging":[135],"small":[137],"LLMs":[138],"vector":[140],"database":[141],"filtering":[142],"construct":[144],"high-quality":[145],"query-document":[146],"pairs.Experiments":[147],"diverse":[149],"medical":[150],"non-IID":[151],"document":[152],"datasets":[153],"demonstrate":[154],"that":[155],"significantly":[157],"reduces":[158],"communication":[159],"costs,":[160],"handles":[161],"improves":[165],"retrieval":[166],"performance.Human":[167],"evaluations":[168],"confirm":[169],"the":[170],"enhanced":[171],"response":[172],"quality":[173],"pFedRAG.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}