{"id":"https://openalex.org/W4416035883","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.188","title":"LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models","display_name":"LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035883","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.188"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.188","pdf_url":"https://aclanthology.org/2025.findings-emnlp.188.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.188.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113066179","display_name":"Ruhong Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijie Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yueyang Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueyang Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048769631","display_name":"Han Hu","orcid":"https://orcid.org/0000-0002-3755-7342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanxu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465137","display_name":"Yingming Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingming Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Lam","orcid":"https://orcid.org/0000-0001-5479-377X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huajian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huajian Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101128711","display_name":"Hongyuan Lu","orcid":"https://orcid.org/0000-0001-9763-7865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyuan Lu","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3512","last_page":"3528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.35899999737739563,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.35899999737739563,"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":0.1420000046491623,"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":0.062300000339746475,"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/contamination","display_name":"Contamination","score":0.32350000739097595},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.32010000944137573},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25380000472068787},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.250900000333786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5187000036239624},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3082999885082245},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24799999594688416},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.24469999969005585}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.188","pdf_url":"https://aclanthology.org/2025.findings-emnlp.188.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.188","pdf_url":"https://aclanthology.org/2025.findings-emnlp.188.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035883.pdf","grobid_xml":"https://content.openalex.org/works/W4416035883.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"problem":[1,28],"of":[2,12,37,62,85,96,145],"data":[3,20,146],"contamination":[4,55,65,77,86],"is":[5,109],"now":[6],"almost":[7],"inevitable":[8],"during":[9],"the":[10,18,70,72,76,83,88,94,97,106,110,115,149],"development":[11],"large":[13],"language":[14],"models":[15,141],"(LLMs),":[16],"with":[17,121,128],"training":[19],"commonly":[21],"integrating":[22],"those":[23],"evaluation":[24],"benchmarks":[25],"even":[26],"unintentionally.This":[27],"subsequently":[29],"makes":[30],"it":[31,92,133],"hard":[32],"to":[33,49,54,81,101,112,154],"benchmark":[34],"LLMs":[35],"fairly.Instead":[36],"constructing":[38],"contaminationfree":[39],"datasets":[40,127],"(quite":[41],"hard),":[42],"we":[43],"propose":[44],"a":[45,122],"novel":[46],"framework,":[47],"LNE-Blocking,":[48],"restore":[50,114],"model":[51],"performance":[52,124],"prior":[53],"on":[56,90,125],"potentially":[57],"leaked":[58],"datasets.Our":[59],"framework":[60,73,108],"consists":[61],"two":[63],"components:":[64],"detection":[66,78],"and":[67,132,142],"disruption":[68,98],"operation.For":[69],"prompt,":[71],"first":[74,111],"uses":[75],"method,":[79],"LNE,":[80],"assess":[82],"extent":[84],"in":[87],"model.Based":[89],"this,":[91],"adjusts":[93],"intensity":[95],"operation,":[99],"Blocking,":[100],"elicit":[102],"non-memorized":[103],"responses":[104],"from":[105],"model.Our":[107],"efficiently":[113],"model's":[116],"greedy":[117],"decoding":[118],"performance.This":[119],"comes":[120],"strong":[123],"multiple":[126],"potential":[129],"leakage":[130],"risks,":[131],"consistently":[134],"achieves":[135],"stable":[136],"recovery":[137],"results":[138],"across":[139],"different":[140],"varying":[143],"levels":[144],"contamination.We":[147],"release":[148],"code":[150],"at":[151],"https://github.com/":[152],"RuijieH/LNE-Blocking":[153],"facilitate":[155],"research.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}