{"id":"https://openalex.org/W4387156572","doi":"https://doi.org/10.48550/arxiv.2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","display_name":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387156572","doi":"https://doi.org/10.48550/arxiv.2309.14717"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.14717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14717","pdf_url":"https://arxiv.org/pdf/2309.14717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.14717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102416541","display_name":"Yuhui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Yuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Lingxi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398927","display_name":"Xiaotao Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Xiaotao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624798","display_name":"Xin Chen","orcid":"https://orcid.org/0009-0005-0200-2493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027050251","display_name":"Heng Chang","orcid":"https://orcid.org/0000-0002-4978-8041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Heng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010146234","display_name":"Hengheng Zhang","orcid":"https://orcid.org/0000-0001-5872-5985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hengheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Zhengsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhengsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667567","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0002-0092-6474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaopeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Qi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102416541"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9854999780654907,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9763000011444092,"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/quantization","display_name":"Quantization (signal processing)","score":0.824316680431366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387970089912415},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5455141067504883},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5287615656852722},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4459293782711029},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4244571924209595},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30918604135513306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2887292504310608},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13778841495513916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09716129302978516},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09159073233604431}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.824316680431366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387970089912415},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5455141067504883},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5287615656852722},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4459293782711029},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4244571924209595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30918604135513306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2887292504310608},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13778841495513916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09716129302978516},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09159073233604431},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.14717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14717","pdf_url":"https://arxiv.org/pdf/2309.14717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.14717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.14717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.14717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14717","pdf_url":"https://arxiv.org/pdf/2309.14717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387156572.pdf","grobid_xml":"https://content.openalex.org/works/W4387156572.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W2152992791","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2112835755","https://openalex.org/W2766405861","https://openalex.org/W4291951920"],"abstract_inverted_index":{"Recently":[0],"years":[1],"have":[2],"witnessed":[3],"a":[4,45,90,133],"rapid":[5],"development":[6],"of":[7,28,58,60,76,78,83,93,138],"large":[8],"language":[9],"models":[10],"(LLMs).":[11],"Despite":[12],"the":[13,20,26,55,65,74,98,107,124,144],"strong":[14],"ability":[15],"in":[16,54,154],"many":[17],"language-understanding":[18],"tasks,":[19],"heavy":[21],"computational":[22],"burden":[23],"largely":[24],"restricts":[25],"application":[27],"LLMs":[29],"especially":[30],"when":[31],"one":[32],"needs":[33],"to":[34,68,115,143],"deploy":[35],"them":[36],"onto":[37],"edge":[38],"devices.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"quantization-aware":[46],"low-rank":[47],"adaptation":[48],"(QA-LoRA)":[49],"algorithm.":[50],"The":[51],"motivation":[52],"lies":[53],"imbalanced":[56],"degrees":[57],"freedom":[59,77],"quantization":[61,79],"and":[62,64,95,118,126,146,150,158],"adaptation,":[63],"solution":[66],"is":[67,86],"use":[69],"group-wise":[70],"operators":[71],"which":[72],"increase":[73],"degree":[75],"meanwhile":[80],"decreasing":[81],"that":[82],"adaptation.":[84],"QA-LoRA":[85,142],"easily":[87],"implemented":[88],"with":[89,101],"few":[91],"lines":[92],"code,":[94],"it":[96],"equips":[97],"original":[99],"LoRA":[100],"two-fold":[102],"abilities:":[103],"(i)":[104],"during":[105],"fine-tuning,":[106,123],"LLM's":[108],"weights":[109,128],"are":[110,129],"quantized":[111,134],"(e.g.,":[112],"into":[113,132],"INT4)":[114],"reduce":[116],"time":[117],"memory":[119],"usage;":[120],"(ii)":[121],"after":[122],"LLM":[125],"auxiliary":[127],"naturally":[130],"integrated":[131],"model":[135,148],"without":[136],"loss":[137],"accuracy.":[139],"We":[140],"apply":[141],"LLaMA":[145],"LLaMA2":[147],"families":[149],"validate":[151],"its":[152],"effectiveness":[153],"different":[155],"fine-tuning":[156],"datasets":[157],"downstream":[159],"scenarios.":[160],"Code":[161],"will":[162],"be":[163],"made":[164],"available":[165],"at":[166],"https://github.com/yuhuixu1993/qa-lora.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}