{"id":"https://openalex.org/W7140080578","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.282","title":"DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance","display_name":"DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140080578","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.282"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.282","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.282","pdf_url":"https://aclanthology.org/2026.findings-eacl.282.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.282.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033589584","display_name":"Seffi Cohen","orcid":"https://orcid.org/0000-0002-1135-0079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seffi Cohen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308968","display_name":"Nurit Cohen Inger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nurit Cohen Inger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002551807","display_name":"Niv Goldshlager","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niv Goldshlager","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086920790","display_name":"Bracha Shapira","orcid":"https://orcid.org/0000-0003-4943-9324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bracha Shapira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012622155","display_name":"Lior Rokach","orcid":"https://orcid.org/0000-0002-6956-3341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lior Rokach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.37559872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5326","last_page":"5336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10828","display_name":"Biometric Identification and Security","score":0.36899998784065247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10828","display_name":"Biometric Identification and Security","score":0.36899998784065247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11800","display_name":"User Authentication and Security Systems","score":0.03779999911785126,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.02199999988079071,"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/fingerprint","display_name":"Fingerprint (computing)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3271999955177307},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.31769999861717224},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27129998803138733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2702000141143799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620199978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545199990272522},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.282","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.282","pdf_url":"https://aclanthology.org/2026.findings-eacl.282.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.282","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.282","pdf_url":"https://aclanthology.org/2026.findings-eacl.282.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140080578.pdf","grobid_xml":"https://content.openalex.org/works/W7140080578.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"demonstrate":[4],"impressive":[5],"capabilities":[6],"but":[7],"exhibit":[8],"inconsistent":[9],"performance":[10,99],"across":[11,102],"diverse":[12,59],"domains.We":[13],"propose":[14],"DFPE":[15,82],"(Diverse":[16],"Fingerprint":[17],"Ensemble),":[18],"a":[19,84,123],"novel":[20],"training-free":[21],"method":[22],"that":[23,122,130],"systematically":[24],"constructs":[25],"subject-adaptive":[26],"ensembles":[27],"by":[28],"balancing":[29],"model":[30,62],"diversity":[31],"and":[32,64,115,135,143],"competence.DFPE":[33],"introduces":[34],"three":[35],"key":[36],"innovations:":[37],"(1)":[38],"semantic":[39],"fingerprinting":[40],"using":[41],"averaged":[42],"response":[43],"embeddings":[44],"to":[45,57,69,126],"capture":[46],"distinct":[47],"problem-solving":[48],"patterns,":[49],"(2)":[50],"DBSCAN-based":[51],"clustering":[52],"with":[53,106],"quantile-based":[54],"competence":[55],"filtering":[56],"ensure":[58],"yet":[60],"capable":[61],"selection,":[63],"(3)":[65],"exponentially-weighted":[66],"aggregation":[67],"adapted":[68],"subject-specific":[70,133],"performance.Our":[71],"method's":[72],"effectiveness":[73],"is":[74,100],"highlighted":[75],"on":[76,113,118,147],"the":[77,91,141],"challenging":[78],"MMLU-pro":[79],"benchmark,":[80],"where":[81],"achieves":[83],"striking":[85],"17.1":[86],"percentage":[87],"point":[88],"gain":[89],"over":[90],"best":[92],"single":[93],"model,":[94],"reaching":[95],"71.4%":[96],"accuracy.This":[97],"strong":[98],"consistent":[101],"other":[103],"standard":[104],"benchmarks,":[105],"significant":[107],"accuracy":[108],"improvements":[109],"of":[110,145],"4.4":[111],"points":[112,117],"AGIEval":[114],"2.7":[116],"MMLU.Our":[119],"results":[120],"underscore":[121],"systematic":[124],"approach":[125],"ensemble":[127],"construction":[128],"-one":[129],"balances":[131],"diversity,":[132],"competence,":[134],"adaptive":[136],"weighting,":[137],"can":[138],"substantially":[139],"enhance":[140],"generalization":[142],"robustness":[144],"LLMs":[146],"multifaceted":[148],"language":[149],"understanding":[150],"tasks.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}