{"id":"https://openalex.org/W4396648407","doi":"https://doi.org/10.1145/3653081.3653102","title":"Retrieval-Augmented Generation with Quantized Large Language Models: A Comparative Analysis","display_name":"Retrieval-Augmented Generation with Quantized Large Language Models: A Comparative Analysis","publication_year":2023,"publication_date":"2023-11-24","ids":{"openalex":"https://openalex.org/W4396648407","doi":"https://doi.org/10.1145/3653081.3653102"},"language":"en","primary_location":{"id":"doi:10.1145/3653081.3653102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653081.3653102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 5th International Conference on Internet of Things, Automation and Artificial Intelligence","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/A5081700159","display_name":"Shanglin Yang","orcid":"https://orcid.org/0009-0007-9957-5689"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shanglin Yang","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096365506","display_name":"Jialin Zhu","orcid":"https://orcid.org/0009-0003-1155-3559"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Zhu","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033912164","display_name":"J. P. Wang","orcid":"https://orcid.org/0000-0003-2686-3755"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Wang","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052729833","display_name":"Xiaohan Xu","orcid":"https://orcid.org/0000-0002-8479-3532"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Xu","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079294562","display_name":"Zihang Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Shao","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103282079","display_name":"Liwei Yao","orcid":"https://orcid.org/0009-0001-1399-4652"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwei Yao","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029509926","display_name":"Benchang Zheng","orcid":"https://orcid.org/0000-0003-2806-8747"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benchang Zheng","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114950340","display_name":"Hu Huang","orcid":"https://orcid.org/0009-0008-3798-2518"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Huang","raw_affiliation_strings":["Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China"],"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Laboratory, China Academy of Launch Vehicle Technology, China","institution_ids":["https://openalex.org/I68581759"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5081700159"],"corresponding_institution_ids":["https://openalex.org/I68581759"],"apc_list":null,"apc_paid":null,"fwci":0.5219,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73847383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9883000254631042,"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":0.8392865657806396},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.611443817615509},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6014934182167053},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5881452560424805},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.56309974193573},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5390772819519043},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5387687683105469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45826607942581177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41212737560272217},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3262655735015869},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1852443516254425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392865657806396},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.611443817615509},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6014934182167053},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5881452560424805},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.56309974193573},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5390772819519043},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5387687683105469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45826607942581177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41212737560272217},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3262655735015869},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1852443516254425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653081.3653102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653081.3653102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 5th International Conference on Internet of Things, Automation and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2998702515","https://openalex.org/W4212774754","https://openalex.org/W4285294723","https://openalex.org/W4324304837","https://openalex.org/W4362515116","https://openalex.org/W4386437475"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Large":[0],"language":[1,172],"models":[2,21,113],"have":[3],"demonstrated":[4],"emergent":[5],"intelligence":[6],"and":[7,27,47,70,106,125,141,160],"ability":[8],"to":[9,43],"handle":[10],"a":[11,32],"wide":[12],"array":[13],"of":[14,19,24,38,101,170],"tasks.":[15,51],"However,":[16],"the":[17,36,45,55,81,99],"reliability":[18],"these":[20],"in":[22,49,58,62,166],"terms":[23],"factual":[25],"accuracy":[26],"timely":[28],"knowledge":[29],"acquisition":[30],"remains":[31],"challenge.":[33],"Researchers":[34],"explore":[35],"implementation":[37],"retrieval-augmented":[39,93],"generation":[40,94],"methods,":[41],"aiming":[42],"enhance":[44],"authenticity":[46],"specificity":[48],"knowledge-intensive":[50],"This":[52],"paper":[53,151],"discusses":[54],"practical":[56,145],"application":[57],"industrial":[59],"settings,":[60],"particularly":[61],"assisting":[63],"design":[64],"personnel":[65],"with":[66,77,153],"navigating":[67],"complex":[68],"standards":[69],"quality":[71],"manuals.":[72],"Utilizing":[73],"an":[74],"open-source":[75],"model":[76,123,158],"6":[78],"billion":[79],"parameters,":[80],"study":[82],"employs":[83],"quantization":[84,116,134],"technology":[85],"for":[86,137,147,163],"local":[87],"deployment,":[88],"addressing":[89],"computational":[90],"challenges.":[91],"The":[92,128,150],"framework":[95],"is":[96,135],"analyzed,":[97],"emphasizing":[98],"integration":[100],"document":[102,139],"parsing,":[103],"vector":[104],"databases,":[105],"text":[107],"embedding":[108],"models.":[109,173],"Experimental":[110],"results":[111],"compare":[112],"at":[114],"different":[115],"levels,":[117],"revealing":[118],"trade-offs":[119],"between":[120],"response":[121],"time,":[122],"size,":[124],"performance":[126,165],"metrics.":[127],"findings":[129],"suggest":[130],"that":[131],"4-bit":[132],"integer":[133],"optimal":[136],"standard":[138],"retrieval":[140],"question-answering":[142],"tasks,":[143],"highlighting":[144],"considerations":[146],"CPU":[148],"inference.":[149],"concludes":[152],"insights":[154],"into":[155],"hyper-parameter":[156],"tuning,":[157],"comparisons,":[159],"future":[161],"optimizations":[162],"enhanced":[164],"edge":[167],"device":[168],"deployments":[169],"large":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
