{"id":"https://openalex.org/W7160997664","doi":"https://doi.org/10.48550/arxiv.2605.12345","title":"Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation","display_name":"Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160997664","doi":"https://doi.org/10.48550/arxiv.2605.12345"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.12345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12345","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.12345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078540874","display_name":"Michela Lorandi","orcid":"https://orcid.org/0000-0002-6131-8763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorandi, Michela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136048605","display_name":"Anya Belz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Belz, Anya","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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7278000116348267,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7278000116348267,"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/T10028","display_name":"Topic Modeling","score":0.19550000131130219,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.006500000134110451,"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/task","display_name":"Task (project management)","score":0.6484000086784363},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/composability","display_name":"Composability","score":0.510699987411499},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.414900004863739},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.3905999958515167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542999982833862},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2778814252","wikidata":"https://www.wikidata.org/wiki/Q5156715","display_name":"Composability","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48080000281333923},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.12345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12345","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.12345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12345","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1,6,19],"(PEFT)":[2],"techniques":[3],"offer":[4],"task-specific":[5],"at":[7,46,59],"a":[8,106],"fraction":[9],"of":[10,13,32,41,52,64,85,119],"the":[11,49,62,79,117,124,134],"cost":[12],"full":[14],"fine-tuning,":[15],"but":[16],"require":[17],"separate":[18],"for":[20,90,152],"every":[21],"new":[22],"task":[23],"(combination).":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"explore":[29],"three":[30,74,83],"ways":[31],"generalising":[33],"beyond":[34],"single-task":[35,130,135],"training/inference:":[36],"(i)":[37],"training":[38],"on":[39,73,133],"combinations":[40],"multiple,":[42],"related":[43],"datasets;":[44],"(ii)":[45],"inference,":[47,60],"composing":[48,61],"weight":[50],"matrices":[51],"separately":[53,65],"trained":[54,66],"PEFT":[55,67,80,102],"modules;":[56],"and":[57,82,95],"(iii)":[58],"outputs":[63,104],"modules.":[68],"We":[69,98],"test":[70,136],"these":[71],"approaches":[72],"different":[75],"LLMs,":[76],"QLoRA":[77],"as":[78],"technique,":[81],"sets":[84],"controlled":[86],"text":[87],"generation":[88],"datasets":[89],"sentiment":[91,153],"control,":[92,94],"topic":[93],"multi-attribute":[96],"control.":[97,154],"find":[99],"that":[100],"summing":[101],"module":[103],"is":[105,123],"particularly":[107],"strong":[108],"composition":[109,141],"method,":[110],"which":[111],"consistently":[112],"either":[113],"outperforms":[114],"or":[115],"matches":[116],"performance":[118,147],"alternative":[120],"approaches.":[121],"This":[122],"case":[125],"even":[126],"when":[127],"comparing":[128],"against":[129],"specialised":[131],"modules":[132],"set,":[137],"where":[138],"three-module":[139],"output":[140],"achieves":[142],"an":[143],"average":[144],"2%":[145],"point":[146],"increase":[148],"across":[149],"all":[150],"models":[151]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-14T00:00:00"}