{"id":"https://openalex.org/W7140072910","doi":"https://doi.org/10.18653/v1/2026.eacl-long.80","title":"RoZO: Geometry-Aware Zeroth-Order Fine-Tuning on Low-Rank Adapters for Black-Box Large Language Models","display_name":"RoZO: Geometry-Aware Zeroth-Order Fine-Tuning on Low-Rank Adapters for Black-Box Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140072910","doi":"https://doi.org/10.18653/v1/2026.eacl-long.80"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.80","pdf_url":"https://aclanthology.org/2026.eacl-long.80.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 19th Conference of the European Chapter 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/2026.eacl-long.80.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130368048","display_name":"Zichen Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zichen Song","raw_affiliation_strings":["Lanzhou University Sungkyunkwan University Lanzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University Sungkyunkwan University Lanzhou University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130363701","display_name":"Weijia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijia Li","raw_affiliation_strings":["Lanzhou University Sungkyunkwan University Lanzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University Sungkyunkwan University Lanzhou University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"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":0.39119415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1773","last_page":"1783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.11969999969005585,"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":0.11969999969005585,"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":0.11400000005960464,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.06759999692440033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3221000134944916},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3005000054836273},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.27140000462532043},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.26350000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6611999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3815000057220459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24969999492168427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24490000307559967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.80","pdf_url":"https://aclanthology.org/2026.eacl-long.80.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.80","pdf_url":"https://aclanthology.org/2026.eacl-long.80.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140072910.pdf","grobid_xml":"https://content.openalex.org/works/W7140072910.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"across":[8],"a":[9,95],"wide":[10],"range":[11],"of":[12,65,75,107],"tasks,":[13],"yet":[14],"fine-tuning":[15],"them":[16],"efficiently":[17],"under":[18],"black-box":[19],"or":[20],"memory-constrained":[21],"settings":[22],"remains":[23],"challenging.Parameter-efficient":[24],"finetuning":[25],"(PEFT)":[26],"techniques":[27],"such":[28,54],"as":[29,55],"LoRA":[30,76,109],"alleviate":[31],"memory":[32],"usage":[33],"by":[34,47],"restricting":[35],"updates":[36,102,113],"to":[37,61,103,134],"low-rank":[38,59],"adapters,":[39],"while":[40],"zeroth-order":[41,97],"(ZO)":[42],"optimization":[43,98],"further":[44],"avoids":[45],"back-propagation":[46],"estimating":[48],"gradients":[49],"from":[50,80],"function":[51],"evaluations.Recent":[52],"work,":[53],"LOZO,":[56],"leverages":[57],"random":[58],"perturbations":[60],"reduce":[62],"the":[63,71,104,108],"variance":[64,128],"ZO":[66,136],"estimates,":[67],"but":[68],"it":[69],"overlooks":[70],"intrinsic":[72],"geometric":[73],"structure":[74],"adapters":[77],"and":[78,83,119,130],"suffers":[79],"unstable":[81],"convergence":[82],"limited":[84],"integration":[85],"with":[86,114],"adaptive":[87,117],"optimizers.To":[88],"address":[89],"these":[90],"limitations,":[91],"we":[92],"propose":[93],"RoZO,":[94],"Riemannian":[96],"framework":[99],"that":[100],"constrains":[101],"tangent":[105],"space":[106],"manifold.By":[110],"exploiting":[111],"geometry-aware":[112],"parallel":[115],"transport,":[116],"preconditioning,":[118],"trust-region":[120],"control,":[121],"RoZO":[122],"achieves":[123],"more":[124],"stable":[125],"convergence,":[126],"tighter":[127],"bounds,":[129],"superior":[131],"performance":[132],"compared":[133],"existing":[135],"methods.":[137]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}