{"id":"https://openalex.org/W7147619611","doi":"https://doi.org/10.1109/icaiic68212.2026.11454167","title":"Design and Verification of a Query-Aware External Memory Pipeline for Small Language Models","display_name":"Design and Verification of a Query-Aware External Memory Pipeline for Small Language Models","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7147619611","doi":"https://doi.org/10.1109/icaiic68212.2026.11454167"},"language":null,"primary_location":{"id":"doi:10.1109/icaiic68212.2026.11454167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic68212.2026.11454167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5110091986","display_name":"SeoWan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seowan Kim","raw_affiliation_strings":["Inje University,Department of Healthcare IT,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inje University,Department of Healthcare IT,Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132632708","display_name":"Sungmoon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungmoon Park","raw_affiliation_strings":["Inje University,Department of Healthcare IT,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inje University,Department of Healthcare IT,Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132576552","display_name":"Hwansuk Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwansuk Choi","raw_affiliation_strings":["College of AI&#x00B7;Software Convergence, Kyungnam University,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of AI&#x00B7;Software Convergence, Kyungnam University,Republic of Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125636932","display_name":"Namhyun Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namhyun Yoo","raw_affiliation_strings":["Kyungnam University,Department of Computer Engineering,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungnam University,Department of Computer Engineering,Republic of Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860745","display_name":"Jinhong Yang","orcid":"https://orcid.org/0000-0002-7756-0263"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhong Yang","raw_affiliation_strings":["Inje University,Department of Healthcare IT,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inje University,Department of Healthcare IT,Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47231295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"683","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.49950000643730164,"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":0.49950000643730164,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0706000030040741,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.049300000071525574,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6345000267028809},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6276000142097473},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6176000237464905},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5521000027656555},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.453900009393692},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4499000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482999801635742},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5521000027656555},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C2779280203","wikidata":"https://www.wikidata.org/wiki/Q17121211","display_name":"Small data","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic68212.2026.11454167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic68212.2026.11454167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":5,"referenced_works":["https://openalex.org/W1987292658","https://openalex.org/W2889787757","https://openalex.org/W2970641574","https://openalex.org/W3115947671","https://openalex.org/W4415428439"],"related_works":[],"abstract_inverted_index":{"While":[0],"the":[1,11,41,55,80,85,97,111,147],"utilization":[2],"of":[3,15,105],"Small":[4],"Language":[5],"Models":[6],"(sLMs)":[7],"has":[8],"recently":[9],"expanded,":[10],"limited":[12],"context":[13],"window":[14],"approximately":[16],"2,048":[17],"tokens":[18,129],"serves":[19],"as":[20],"a":[21,48,101,107,124,131],"critical":[22],"bottleneck":[23],"in":[24,119,128,135],"long-term":[25],"memory":[26],"tasks.":[27],"Conventional":[28],"truncation":[29,112],"or":[30],"simple":[31],"summarization":[32],"techniques":[33],"lead":[34],"to":[35,60,72,79],"information":[36,77],"loss":[37],"and":[38,130,142,150],"distortion,":[39],"causing":[40],"\u201ccatastrophic":[42],"forgetting\u201d":[43],"problem.":[44],"This":[45,64],"study":[46],"proposes":[47],"\u201cQuery-Aware":[49],"External":[50],"Memory":[51],"Pipeline\u201d":[52],"inspired":[53],"by":[54],"human":[56],"\u201cSelective":[57],"Attention\u201d":[58],"mechanism":[59],"address":[61],"this":[62],"issue.":[63],"methodology":[65],"combines":[66],"importance":[67],"extraction":[68],"with":[69],"embedding-based":[70],"filtering":[71],"dynamically":[73],"retrieve":[74],"only":[75],"key":[76],"relevant":[78],"query.":[81],"Extensive":[82],"experiments":[83,139],"using":[84],"2WikiMultiHopQA":[86],"dataset":[87],"(<tex":[88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathrm{N}":[90],"=":[91],"500$</tex>,":[92],"10":[93],"iterations)":[94],"demonstrate":[95],"that":[96],"proposed":[98],"method":[99],"achieves":[100],"Fact":[102],"Recovery":[103],"rate":[104],"72.00%,":[106],"6-fold":[108],"improvement":[109],"over":[110],"method.":[113],"Furthermore,":[114],"it":[115],"validates":[116],"high":[117],"applicability":[118],"limited-context":[120],"sLM":[121],"environments":[122],"through":[123],"79":[125],"%":[126,133],"reduction":[127,134],"43":[132],"inference":[136],"time.":[137],"Comparative":[138],"between":[140],"Gemma2":[141],"Llama2":[143],"models":[144],"also":[145],"confirmed":[146],"method's":[148],"versatility":[149],"reliability.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}