{"id":"https://openalex.org/W7154583742","doi":"https://doi.org/10.48550/arxiv.2604.13368","title":"TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models","display_name":"TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154583742","doi":"https://doi.org/10.48550/arxiv.2604.13368"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13368","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.13368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000497388","display_name":"Yarui Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yarui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133778562","display_name":"Kai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kai","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":null,"has_fulltext":false,"cited_by_count":0,"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":0.2816999852657318,"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":0.2816999852657318,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13189999759197235,"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":0.0957999974489212,"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/robustness","display_name":"Robustness (evolution)","score":0.682699978351593},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.574999988079071},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5658000111579895},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4848000109195709},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41780000925064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.682699978351593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.574999988079071},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214999914169312},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45590001344680786},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C128099668","wikidata":"https://www.wikidata.org/wiki/Q573952","display_name":"Lazy evaluation","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.27559998631477356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13368","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:10.48550/arxiv.2604.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13368","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4087885618209839}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2],"models":[3,9],"(LLMs)":[4],"aims":[5],"to":[6,10],"adapt":[7],"pre-trained":[8,60],"specific":[11],"tasks":[12],"using":[13],"relatively":[14],"small":[15],"and":[16,100],"domain-specific":[17],"datasets.":[18],"Among":[19],"Parameter-Efficient":[20],"Fine-Tuning":[21],"(PEFT)":[22],"methods,":[23],"Low-Rank":[24],"Adaptation":[25],"(LoRA)":[26],"stands":[27],"out":[28],"by":[29],"matching":[30],"the":[31,52,56,68,87,98],"performance":[32,77],"of":[33,59,70,102],"full":[34],"fine-tuning":[35],"while":[36],"avoiding":[37],"additional":[38],"inference":[39],"latency.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46],"novel":[47],"PEFT":[48],"method":[49],"that":[50],"incorporates":[51],"TLoRA+":[53],"optimizer":[54],"into":[55],"weight":[57],"matrices":[58],"models.":[61],"The":[62],"proposed":[63,104],"approach":[64],"not":[65],"only":[66],"preserves":[67],"efficiency":[69],"low-rank":[71],"adaptation":[72],"but":[73],"also":[74],"further":[75],"enhances":[76],"without":[78],"significantly":[79],"increasing":[80],"computational":[81],"cost.":[82],"We":[83],"conduct":[84],"experiments":[85,95],"on":[86],"GLUE":[88],"benchmark":[89],"across":[90],"diverse":[91],"model":[92],"architectures.":[93],"Numerical":[94],"consistently":[96],"demonstrate":[97],"effectiveness":[99],"robustness":[101],"our":[103],"method.":[105]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-17T00:00:00"}