{"id":"https://openalex.org/W4409282487","doi":"https://doi.org/10.1145/3676536.3676674","title":"Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures","display_name":"Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409282487","doi":"https://doi.org/10.1145/3676536.3676674"},"language":"en","primary_location":{"id":"doi:10.1145/3676536.3676674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676536.3676674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design","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/A5106463942","display_name":"Ruiyang Qin","orcid":"https://orcid.org/0000-0003-0827-2257"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruiyang Qin","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059093077","display_name":"Zheyu Yan","orcid":"https://orcid.org/0000-0003-1830-606X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheyu Yan","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108216240","display_name":"Dawen Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dewen Zeng","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027997476","display_name":"Zhenge Jia","orcid":"https://orcid.org/0000-0002-0554-3608"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenge Jia","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020157237","display_name":"Dancheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dancheng Liu","raw_affiliation_strings":["University at Buffalo--SUNY, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"University at Buffalo--SUNY, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001894797","display_name":"Jianbo Liu","orcid":"https://orcid.org/0000-0003-4768-7797"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianbo Liu","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016943900","display_name":"Ahmed Abbasi","orcid":"https://orcid.org/0000-0001-7698-7794"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Abbasi","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103030867","display_name":"Zhi Zheng","orcid":"https://orcid.org/0000-0001-5274-8721"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Zheng","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031804347","display_name":"Ningyuan Cao","orcid":"https://orcid.org/0000-0002-5323-1051"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ningyuan Cao","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075633314","display_name":"Kai Ni","orcid":"https://orcid.org/0000-0002-3628-3431"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Ni","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["University at Buffalo--SUNY, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"University at Buffalo--SUNY, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141831","display_name":"Yiyu Shi","orcid":"https://orcid.org/0000-0002-6788-9823"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5106463942"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":1.4614,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8301182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.8174119591712952},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5277281999588013},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5258791446685791},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5025284290313721},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48750779032707214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327505886554718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174119591712952},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5277281999588013},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5258791446685791},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5025284290313721},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48750779032707214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327505886554718}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676536.3676674","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676536.3676674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design","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":30,"referenced_works":["https://openalex.org/W2022322548","https://openalex.org/W2030214786","https://openalex.org/W2322411027","https://openalex.org/W2604319603","https://openalex.org/W2795127895","https://openalex.org/W3003821665","https://openalex.org/W3022053993","https://openalex.org/W3027879771","https://openalex.org/W3037702185","https://openalex.org/W3127168173","https://openalex.org/W3203717475","https://openalex.org/W3212633509","https://openalex.org/W4224295775","https://openalex.org/W4226216109","https://openalex.org/W4229779967","https://openalex.org/W4244661214","https://openalex.org/W4293023010","https://openalex.org/W4323927861","https://openalex.org/W4377197101","https://openalex.org/W4386894249","https://openalex.org/W4388032243","https://openalex.org/W4389166756","https://openalex.org/W4389260942","https://openalex.org/W4390832893","https://openalex.org/W4391807506","https://openalex.org/W4399848680","https://openalex.org/W6777615688","https://openalex.org/W6803771590","https://openalex.org/W6859868774","https://openalex.org/W6863994431"],"related_works":["https://openalex.org/W2115140794","https://openalex.org/W2041120224","https://openalex.org/W1504320321","https://openalex.org/W2067902980","https://openalex.org/W2548529098","https://openalex.org/W4324372666","https://openalex.org/W4225706866","https://openalex.org/W2914646191","https://openalex.org/W3023564924","https://openalex.org/W2942586735"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"deployed":[4],"on":[5,38,70,133],"edge":[6,39,134],"devices":[7],"learn":[8],"through":[9],"fine-tuning":[10],"and":[11,131,172,187],"updating":[12,59],"a":[13,35,45,141,181],"certain":[14],"portion":[15],"of":[16,54,89,102,110,129,203],"their":[17],"parameters.":[18,61],"Although":[19],"such":[20],"learning":[21,48],"methods":[22],"can":[23,50,80,190],"be":[24],"optimized":[25],"to":[26,82,94,123,144,193,213],"reduce":[27],"resource":[28],"utilization,":[29],"the":[30,52,55,63,71,87,100,108,127,160,164,169,201,208],"overall":[31],"required":[32],"resources":[33],"remain":[34],"heavy":[36],"burden":[37],"devices.":[40],"Instead,":[41],"Retrieval-Augmented":[42],"Generation":[43],"(RAG),":[44],"resource-efficient":[46],"LLM":[47,65],"method,":[49],"improve":[51],"quality":[53],"LLM-generated":[56],"content":[57],"without":[58],"model":[60],"However,":[62],"RAG-based":[64],"may":[66],"involve":[67],"repetitive":[68],"searches":[69],"profile":[72,196],"data":[73,114,166,197],"in":[74,98],"every":[75],"user-LLM":[76],"interaction.":[77],"This":[78],"search":[79,195],"lead":[81],"significant":[83],"latency":[84,96,130],"along":[85],"with":[86,198],"accumulation":[88],"user":[90,104,113],"data.":[91],"Conventional":[92],"efforts":[93],"decrease":[95],"result":[97],"restricting":[99],"size":[101],"saved":[103],"data,":[105],"thus":[106],"reducing":[107],"scalability":[109,132],"RAG":[111,125,146,178,192],"as":[112],"continuously":[115],"grows.":[116],"It":[117,151],"remains":[118],"an":[119],"open":[120],"question:":[121],"how":[122],"free":[124],"from":[126],"constraints":[128],"devices?":[135],"In":[136],"this":[137,206],"paper,":[138],"we":[139],"propose":[140],"novel":[142,182],"framework":[143],"accelerate":[145,214],"via":[147],"Computing-in-Memory":[148],"(CiM)":[149],"architectures.":[150],"accelerates":[152],"matrix":[153],"multiplications":[154],"by":[155],"performing":[156],"in-situ":[157],"computation":[158],"inside":[159],"memory":[161],"while":[162],"avoiding":[163],"expensive":[165],"transfer":[167],"between":[168],"computing":[170],"unit":[171],"memory.":[173],"Our":[174],"framework,":[175],"Robust":[176],"CiM-backed":[177],"(RoCR),":[179],"utilizing":[180,211],"contrastive":[183],"learning-based":[184],"training":[185],"method":[186],"noise-aware":[188],"training,":[189],"enable":[191],"efficiently":[194],"CiM.":[199],"To":[200],"best":[202],"our":[204],"knowledge,":[205],"is":[207],"first":[209],"work":[210],"CiM":[212],"RAG.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}