{"id":"https://openalex.org/W4415744666","doi":"https://doi.org/10.1109/ccci65983.2025.11215121","title":"DS-CAE: a Dual-Stream Cross-Attentive Autoencoder for Robust and Cluster-Aware Retrieval-Augmented Generation","display_name":"DS-CAE: a Dual-Stream Cross-Attentive Autoencoder for Robust and Cluster-Aware Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415744666","doi":"https://doi.org/10.1109/ccci65983.2025.11215121"},"language":null,"primary_location":{"id":"doi:10.1109/ccci65983.2025.11215121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccci65983.2025.11215121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","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/A5104299689","display_name":"Soeun Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soeun Choi","raw_affiliation_strings":["Ewha Womans University,Dept. of Artificial Intelligence Convergence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Dept. of Artificial Intelligence Convergence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696637","display_name":"Yejin Lee","orcid":"https://orcid.org/0000-0001-9532-1621"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yejin Lee","raw_affiliation_strings":["Ewha Womans University,Dept. of Artificial Intelligence Convergence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Dept. of Artificial Intelligence Convergence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048643266","display_name":"Juhee Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhee Kim","raw_affiliation_strings":["Ewha Womans University,Dept. of Studies in Visual Arts,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Dept. of Studies in Visual Arts,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011359988","display_name":"Minji Lee","orcid":"https://orcid.org/0000-0001-7188-370X"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minji Lee","raw_affiliation_strings":["Ewha Womans University,Dept. of Library and Information Science,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Dept. of Library and Information Science,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013362846","display_name":"Jaehyeong Sim","orcid":"https://orcid.org/0000-0001-8722-8486"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyeong Sim","raw_affiliation_strings":["Ewha Womans University,Dept. of Computer Science and Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Dept. of Computer Science and Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104299689"],"corresponding_institution_ids":["https://openalex.org/I138925566"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17651098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.38749998807907104,"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":0.38749998807907104,"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":0.14010000228881836,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13750000298023224,"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/autoencoder","display_name":"Autoencoder","score":0.7343999743461609},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5354999899864197},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5076000094413757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.37229999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734499990940094},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7343999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6697999835014343},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5076000094413757},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccci65983.2025.11215121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccci65983.2025.11215121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1986007546","https://openalex.org/W2067191022","https://openalex.org/W2517760103","https://openalex.org/W2616922365","https://openalex.org/W2777922598","https://openalex.org/W2883725317","https://openalex.org/W2890961898","https://openalex.org/W2912924812","https://openalex.org/W2951434086","https://openalex.org/W2953163841","https://openalex.org/W2962985038","https://openalex.org/W3102659883","https://openalex.org/W3154280800","https://openalex.org/W3156636935","https://openalex.org/W3168875417","https://openalex.org/W3207796810","https://openalex.org/W3217305727","https://openalex.org/W4205332217","https://openalex.org/W4225385501","https://openalex.org/W4296079469","https://openalex.org/W4382449327","https://openalex.org/W4385573862","https://openalex.org/W4389519598","https://openalex.org/W4407691642"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"enhances":[3],"language":[4],"models":[5,112],"by":[6,115],"incorporating":[7],"external":[8],"knowledge":[9],"at":[10],"inference":[11],"time.":[12],"However,":[13],"its":[14],"performance":[15],"is":[16],"highly":[17],"sensitive":[18],"to":[19,117],"the":[20],"quality":[21],"of":[22],"retrieved":[23],"content,":[24],"which":[25],"often":[26,39],"includes":[27],"noisy":[28],"or":[29],"irrelevant":[30],"distractors.":[31],"Conventional":[32],"latent":[33],"representations":[34],"for":[35,75],"clustering-based":[36],"retrieval":[37,80,136],"are":[38],"poorly":[40],"structured":[41],"and":[42,58,63,72,89,96,104,119],"misaligned":[43],"with":[44,69,81,124],"generation":[45],"objectives.":[46],"We":[47,66,78,129],"propose":[48],"DS-CAE,":[49],"a":[50,82,125],"Dual-Stream":[51],"Cross-Attentive":[52],"Autoencoder":[53],"that":[54,107],"jointly":[55],"encodes":[56],"global":[57],"local":[59],"semantics":[60],"via":[61],"Transformer":[62],"BiLSTM":[64],"encoders.":[65],"fuse":[67],"them":[68],"bidirectional":[70],"cross-attention":[71],"token-wise":[73],"gating":[74],"context-aware":[76],"integration.":[77],"improve":[79],"composite":[83],"loss":[84,95],"(reconstruction":[85],"+":[86],"adaptive-margin":[87],"triplet)":[88],"GMM":[90],"filtering":[91],"based":[92],"on":[93,100,113,122,134],"reconstruction":[94],"cluster":[97],"distance.":[98],"Experiments":[99],"Natural":[101],"Questions,":[102],"WebQuestions,":[103],"CuratedTREC":[105,114],"show":[106],"DS-CAE":[108],"outperforms":[109],"previous":[110],"RAG":[111],"up":[116],"6.8%":[118],"performs":[120],"competitively":[121],"NQ":[123],"compact":[126],"171M-parameter":[127],"model.":[128],"validate":[130],"each":[131],"component\u2019s":[132],"impact":[133],"cluster-aware":[135],"through":[137],"ablations.":[138]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-31T00:00:00"}