{"id":"https://openalex.org/W7140187192","doi":"https://doi.org/10.48550/arxiv.2603.21970","title":"Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning","display_name":"Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140187192","doi":"https://doi.org/10.48550/arxiv.2603.21970"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21970","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.2603.21970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shernazarov, Ulugbek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shernazarov, Ulugbek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Svitsov, Rostislav","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Svitsov, Rostislav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shi, Bin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Bin","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":0.6797999739646912,"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":0.6797999739646912,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.22259999811649323,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.009399999864399433,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8220999836921692},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44359999895095825},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.39329999685287476}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8220999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.271699994802475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21970","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.2603.21970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21970","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2],"models":[3],"for":[4,85],"domain-specific":[5],"tasks":[6],"such":[7],"as":[8],"medical":[9,51],"text":[10],"summarization":[11,52],"demands":[12],"substantial":[13],"computational":[14],"resources.":[15],"Parameter-efficient":[16],"fine-tuning":[17],"(PEFT)":[18],"methods":[19],"offer":[20],"promising":[21],"alternatives":[22],"by":[23],"updating":[24],"only":[25,76],"a":[26],"small":[27],"fraction":[28],"of":[29,93,114],"parameters.":[30],"This":[31],"paper":[32],"compares":[33],"three":[34],"adaptation":[35],"approaches-Low-Rank":[36],"Adaptation":[37],"(LoRA),":[38],"Prompt":[39],"Tuning,":[40],"and":[41,96],"Full":[42],"Fine-Tuning-across":[43],"the":[44,49,91,103,112],"Flan-T5":[45],"model":[46],"family":[47],"on":[48,73],"PubMed":[50],"dataset.":[53],"Through":[54],"experiments":[55],"with":[56,75],"multiple":[57],"random":[58],"seeds,":[59],"we":[60],"demonstrate":[61],"that":[62],"LoRA":[63,94],"consistently":[64],"outperforms":[65],"full":[66,86,115],"fine-tuning,":[67],"achieving":[68],"43.52":[69],"+/-":[70,83],"0.18":[71],"ROUGE-1":[72],"Flan-T5-Large":[74],"0.6%":[77],"trainable":[78],"parameters":[79],"compared":[80],"to":[81],"40.67":[82],"0.21":[84],"fine-tuning.":[87],"Sensitivity":[88],"analyses":[89],"examine":[90],"impact":[92],"rank":[95],"prompt":[97],"token":[98],"count.":[99],"Our":[100],"findings":[101],"suggest":[102],"low-rank":[104],"constraint":[105],"provides":[106],"beneficial":[107],"regularization,":[108],"challenging":[109],"assumptions":[110],"about":[111],"necessity":[113],"parameter":[116],"updates.":[117],"Code":[118],"is":[119],"available":[120],"at":[121],"https://github.com/eracoding/llm-medical-summarization":[122]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-25T00:00:00"}