{"id":"https://openalex.org/W4410636396","doi":"https://doi.org/10.1145/3701716.3717578","title":"Optimize Quantization for Large Language Models via Progressive Training","display_name":"Optimize Quantization for Large Language Models via Progressive Training","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636396","doi":"https://doi.org/10.1145/3701716.3717578"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717578","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111227787","display_name":"Jiangcun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangcun Du","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-4760-2985","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074106607","display_name":"Renren Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renren Jin","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-7452-9883","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043416325","display_name":"Wuwei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wuwei Huang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6064-4405","affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Liu","orcid":"https://orcid.org/0009-0009-4327-1920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Xiaomi, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4327-1920","affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2383-226X","affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055232825","display_name":"Deyi Xiong","orcid":"https://orcid.org/0000-0002-2353-5038"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Xiong","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2353-5038","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2474","last_page":"2483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9957000017166138,"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":0.9945999979972839,"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":0.7504557371139526},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6822084784507751},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6206480860710144},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46298137307167053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45766738057136536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32793518900871277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18999189138412476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504557371139526},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6822084784507751},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6206480860710144},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46298137307167053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45766738057136536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32793518900871277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18999189138412476},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G501308975","display_name":null,"funder_award_id":"No. 2023YFE0116400","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636396.pdf","grobid_xml":"https://content.openalex.org/works/W4410636396.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2747329762","https://openalex.org/W2998617917","https://openalex.org/W3081168214","https://openalex.org/W3194676777","https://openalex.org/W4226126941","https://openalex.org/W4327810158","https://openalex.org/W4387321091","https://openalex.org/W4388184238","https://openalex.org/W4391136507","https://openalex.org/W4399115604","https://openalex.org/W4400065085","https://openalex.org/W4401306886","https://openalex.org/W4402667003","https://openalex.org/W4405768363"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Quantization":[0],"has":[1,29],"played":[2],"a":[3],"significant":[4],"role":[5],"in":[6,34],"enabling":[7],"large":[8],"language":[9],"models":[10],"to":[11,83],"operate":[12],"efficiently.":[13],"Quantization-Aware":[14],"Training":[15],"(QAT)":[16],"compensates":[17],"for":[18],"the":[19,23,35,45,57,101,113,116],"loss":[20],"incurred":[21],"during":[22],"quantization":[24,105],"process":[25],"through":[26],"training,":[27],"and":[28,63],"demonstrated":[30],"promising":[31],"results.":[32],"However,":[33],"case":[36],"of":[37,47,73,103,115],"extremely":[38,107],"low-bit":[39,81,108],"quantization,":[40],"such":[41],"as":[42],"3":[43],"bits,":[44],"performance":[46],"QAT":[48,82],"degrades":[49],"significantly.":[50],"In":[51],"this":[52,90],"paper,":[53],"we":[54,67,92],"delve":[55],"into":[56],"challenges":[58],"associated":[59],"with":[60],"data":[61,74],"selection":[62],"training":[64,97],"approach.":[65],"Specifically,":[66],"have":[68],"initially":[69],"analyzed":[70],"which":[71],"type":[72],"yields":[75],"better":[76],"results":[77],"when":[78],"applying":[79],"ultra":[80],"base":[84],"or":[85],"chat":[86],"models.":[87],"Building":[88],"on":[89],"analysis,":[91],"further":[93],"propose":[94],"an":[95],"iterative":[96],"approach":[98],"that":[99],"enhances":[100],"stability":[102],"model":[104],"at":[106],"configuration.":[109],"Experimental":[110],"evaluations":[111],"demonstrate":[112],"effectiveness":[114],"proposed":[117],"method.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}