{"id":"https://openalex.org/W4417413337","doi":"https://doi.org/10.18653/v1/2026.acl-long.106","title":"TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models","display_name":"TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417413337","doi":"https://doi.org/10.18653/v1/2026.acl-long.106"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.106","pdf_url":"https://aclanthology.org/2026.acl-long.106.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.106.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073038540","display_name":"Yixin Gu","orcid":"https://orcid.org/0000-0002-0454-8431"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065141875","display_name":"Wuyang Zhou","orcid":"https://orcid.org/0000-0003-2229-2852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wuyang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094208275","display_name":"Giorgos Iacovides","orcid":"https://orcid.org/0009-0007-5733-8992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgos Iacovides","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103001848","display_name":"Danilo P. Mandic","orcid":"https://orcid.org/0000-0001-8432-3963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danilo Mandic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.03713094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2314","last_page":"2329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.24699999392032623,"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":0.24699999392032623,"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/T12303","display_name":"Tensor decomposition and applications","score":0.09889999777078629,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07699999958276749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5943999886512756},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5781000256538391},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5449000000953674},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44290000200271606},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4196999967098236},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073000073432922},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C2775904623","wikidata":"https://www.wikidata.org/wiki/Q108529","display_name":"Tera-","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C34947359","wikidata":"https://www.wikidata.org/wiki/Q665189","display_name":"Complex network","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.106","pdf_url":"https://aclanthology.org/2026.acl-long.106.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.03234","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.03234","pdf_url":"https://arxiv.org/pdf/2509.03234","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.03234","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.03234","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.106","pdf_url":"https://aclanthology.org/2026.acl-long.106.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 64th Annual Meeting 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/W4417413337.pdf","grobid_xml":"https://content.openalex.org/works/W4417413337.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-Efficient":[0],"Fine-Tuning":[1],"(PEFT)":[2],"methods,":[3],"such":[4],"as":[5,47,58,122,167,171],"Low-Rank":[6],"Adaptation":[7,93],"(LoRA),":[8],"have":[9,28],"significantly":[10],"reduced":[11],"the":[12,60,69,73,106,117,179,182],"number":[13],"of":[14,25,62,71,109,149,181],"trainable":[15,169],"parameters":[16,170],"needed":[17],"in":[18],"fine-tuning":[19],"large":[20,129],"language":[21],"models":[22],"(LLMs).The":[23],"developments":[24],"LoRA-style":[26],"adapters":[27],"considered":[29],"two":[30],"main":[31],"directions:":[32],"(1)":[33],"enhancing":[34],"model":[35],"expressivity":[36,61],"with":[37,55],"high-rank":[38,63,101,163],"adapters,":[39,164],"and":[40,135,175],"(2)":[41],"aiming":[42],"for":[43,91],"further":[44],"parameter":[45,75,107],"reduction,":[46],"exemplified":[48],"by":[49,78,115],"vector-based":[50,79,87,110],"methods.However,":[51],"these":[52],"approaches":[53],"come":[54],"a":[56,86,95,123],"trade-off,":[57],"achieving":[59],"weight":[64,102,119],"updates":[65,103],"typically":[66],"comes":[67],"at":[68,189],"cost":[70],"sacrificing":[72],"extreme":[74],"efficiency":[76,108],"offered":[77],"techniques.To":[80],"address":[81],"this":[82],"issue,":[83],"we":[84],"propose":[85],"random":[88],"Tensor":[89],"network":[90,126],"high-Rank":[92],"(TeRA),":[94],"novel":[96],"PEFT":[97,111],"method":[98],"that":[99,156],"achieves":[100],"while":[104,139,165],"retaining":[105],"adapters.This":[112],"is":[113,187],"achieved":[114],"parametrizing":[116],"tensorized":[118],"update":[120],"matrix":[121],"Tucker-like":[124],"tensor":[125],"(TN),":[127],"whereby":[128],"randomly":[130],"initialized":[131],"factors":[132],"are":[133,152],"frozen":[134],"shared":[136],"across":[137],"layers,":[138],"only":[140],"small":[141],"layer-specific":[142],"scaling":[143],"vectors,":[144],"corresponding":[145],"to":[146],"diagonal":[147],"entries":[148],"factor":[150],"matrices,":[151],"trained.Comprehensive":[153],"experiments":[154],"demonstrate":[155],"TeRA":[157,184],"matches":[158],"or":[159],"even":[160],"outperforms":[161],"existing":[162],"requiring":[166],"few":[168],"vectorbased":[172],"methods.Theoretical":[173],"analysis":[174],"ablation":[176],"studies":[177],"validate":[178],"effectiveness":[180],"proposed":[183],"method.The":[185],"code":[186],"available":[188],"https://github.com/guyuxuan9/TeRA.":[190]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}