{"id":"https://openalex.org/W4412886723","doi":"https://doi.org/10.18653/v1/2025.acl-long.164","title":"Taming LLMs with Gradient Grouping","display_name":"Taming LLMs with Gradient Grouping","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886723","doi":"https://doi.org/10.18653/v1/2025.acl-long.164"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.164","pdf_url":"https://aclanthology.org/2025.acl-long.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.164.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101467829","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0003-0617-2279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Juanxi Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juanxi Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101701783","display_name":"Zedong Wang","orcid":"https://orcid.org/0000-0002-5332-2033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zedong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033127079","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-0935-5329"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061378330","display_name":"Zichen Liu","orcid":"https://orcid.org/0000-0001-6694-6008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119180888","display_name":"Wentao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101994681","display_name":"Dan Xu","orcid":"https://orcid.org/0000-0002-1749-9755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20267797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3260","last_page":"3279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45683854818344116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45683854818344116}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.164","pdf_url":"https://aclanthology.org/2025.acl-long.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148836","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.164","pdf_url":"https://aclanthology.org/2025.acl-long.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G8667662007","display_name":null,"funder_award_id":"R9253","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320318567","display_name":"Westlake University","ror":null},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886723.pdf","grobid_xml":"https://content.openalex.org/works/W4412886723.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"poses":[5],"challenges":[6],"due":[7],"to":[8,84],"their":[9],"massive":[10],"scale":[11],"and":[12,28,40,67,79,113,117,131],"heterogeneous":[13],"architectures.While":[14],"adaptive":[15,60],"optimizers":[16],"like":[17],"AdamW":[18],"help":[19],"address":[20],"gradient":[21,72],"variations,":[22],"they":[23],"still":[24],"struggle":[25],"with":[26,43,51,110,122],"efficient":[27],"effective":[29],"parameter-wise":[30],"learning":[31,61,86,132],"rate":[32,62],"estimation,":[33],"resulting":[34],"in":[35,74],"training":[36],"instability,":[37],"slow":[38],"convergence,":[39],"poor":[41],"compatibility":[42],"parameter-efficient":[44],"fine-tuning":[45],"(PEFT)":[46],"techniques.This":[47],"work":[48],"introduces":[49],"Scaling":[50],"Gradient":[52],"Grouping":[53],"(SGG),":[54],"an":[55],"optimizer":[56],"wrapper":[57],"that":[58,106],"improves":[59],"estimation":[63],"by":[64],"dynamic":[65],"grouping":[66],"group-specific":[68],"scaling.SGG":[69],"first":[70],"groups":[71],"statistics":[73],"each":[75,89],"layer":[76],"into":[77],"clusters":[78],"then":[80],"applies":[81],"cluster-specific":[82],"scaling":[83],"calibrate":[85],"rates":[87,133],"for":[88,140],"parameter,":[90],"thus":[91],"imposing":[92],"collective":[93],"group-wise":[94],"constraints":[95],"while":[96],"maintaining":[97],"precise":[98],"per-parameter":[99],"adaptation.Experiments":[100],"on":[101],"diverse":[102],"(M)LLM":[103],"benchmarks":[104],"show":[105],"SGG":[107,135],"integrates":[108],"seamlessly":[109],"existing":[111],"optimizers,":[112],"offers":[114],"consistent":[115],"gains":[116],"faster":[118],"convergence":[119],"over":[120],"baselines,":[121],"various":[123],"model":[124],"sizes.Its":[125],"stability":[126],"across":[127],"varying":[128],"batch":[129],"sizes":[130],"establishes":[134],"as":[136],"a":[137],"robust":[138],"choice":[139],"LLM":[141],"optimization.":[142]},"counts_by_year":[],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}