{"id":"https://openalex.org/W7160610727","doi":"https://doi.org/10.48550/arxiv.2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","display_name":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160610727","doi":"https://doi.org/10.48550/arxiv.2605.06166"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.06166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135664217","display_name":"Xinrui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135683348","display_name":"Liu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135702801","display_name":"Ou Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Ou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.3849000036716461,"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":0.3849000036716461,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.14339999854564667,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.05889999866485596,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7576000094413757},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4424999952316284},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/model-parameter","display_name":"Model parameter","score":0.3939000070095062},{"id":"https://openalex.org/keywords/scoring-rule","display_name":"Scoring rule","score":0.3930000066757202},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.37130001187324524},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7576000094413757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640500009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4869000017642975},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47029998898506165},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C2983447341","wikidata":"https://www.wikidata.org/wiki/Q1413083","display_name":"Model parameter","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3005000054836273},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.06166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"Large":[1],"Language":[2],"Model":[3],"(LLM)":[4],"fine-tuning,":[5,36],"parameter":[6,28,49,77,119],"and":[7,30,42,50,63,73,79,85,121,137],"data":[8,31,51,80,122],"selection":[9,45,52,56],"are":[10,19],"common":[11,60],"strategies":[12],"for":[13,99],"reducing":[14],"fine-tuning":[15],"cost,":[16],"yet":[17],"they":[18],"typically":[20],"driven":[21],"by":[22],"separate":[23],"scoring":[24,69],"mechanisms.":[25],"When":[26],"a":[27,59,65,89,95,112,118,148],"mask":[29,120],"subset":[32,123],"jointly":[33],"determine":[34],"restricted":[35],"this":[37,105],"separation":[38],"incurs":[39],"redundant":[40],"overhead":[41],"makes":[43],"coordinated":[44],"difficult.":[46],"We":[47],"cast":[48],"as":[53,83],"two":[54],"bilevel":[55],"problems":[57],"under":[58,157],"validation":[61],"objective":[62],"derive":[64],"shared":[66,125],"local":[67],"response-surrogate":[68],"rule.":[70],"Under":[71],"first-":[72],"second-order":[74],"validation-improvement":[75],"approximations,":[76],"importance":[78],"utility":[81],"emerge":[82],"column-wise":[84],"row-wise":[86],"aggregations":[87],"of":[88],"single":[90],"gradient":[91,126],"interaction":[92],"matrix,":[93],"yielding":[94],"closed-form":[96],"row-column":[97],"correspondence":[98],"co-extracting":[100],"both":[101],"signals.":[102],"Building":[103],"on":[104],"structure,":[106],"we":[107],"propose":[108],"DualSFT":[109,132,146],"(Dual-Selection":[110],"Fine-Tuning),":[111],"one-shot":[113],"dual-scoring":[114],"algorithm":[115],"that":[116],"produces":[117],"from":[124],"statistics.":[127],"On":[128],"3B-9B":[129],"LLMs,":[130],"single-axis":[131],"variants":[133],"strengthen":[134],"target-task":[135],"performance":[136],"stability-plasticity":[138],"trade-offs":[139],"within":[140],"their":[141],"comparison":[142],"groups,":[143],"while":[144],"full":[145],"yields":[147],"more":[149],"favorable":[150],"joint-constrained":[151],"trade-off":[152],"than":[153],"sequential":[154],"hybrid":[155],"baselines":[156],"matched":[158],"budgets.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-09T00:00:00"}