{"id":"https://openalex.org/W4416943788","doi":"https://doi.org/10.48550/arxiv.2511.22153","title":"Simplex-Optimized Hybrid Ensemble for Large Language Model Text Detection Under Generative Distribution Drif","display_name":"Simplex-Optimized Hybrid Ensemble for Large Language Model Text Detection Under Generative Distribution Drif","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416943788","doi":"https://doi.org/10.48550/arxiv.2511.22153"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.22153","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22153","pdf_url":"https://arxiv.org/pdf/2511.22153","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.22153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086012195","display_name":"Sepyan Purnama Kristanto","orcid":"https://orcid.org/0000-0002-9073-263X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristanto, Sepyan Purnama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015532052","display_name":"Lutfi Hakim","orcid":"https://orcid.org/0000-0001-6691-1550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakim, Lutfi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yusuf, Dianni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuf, Dianni","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/T12380","display_name":"Authorship Attribution and Profiling","score":0.4250999987125397,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.4250999987125397,"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":0.25029999017715454,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.03229999914765358,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.7178999781608582},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5295000076293945},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4796000123023987},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44690001010894775},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.3718999922275543},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189000248908997},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.7178999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6194999814033508},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44690001010894775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.22153","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22153","pdf_url":"https://arxiv.org/pdf/2511.22153","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.22153","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22153","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.22153","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22153","pdf_url":"https://arxiv.org/pdf/2511.22153","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"The":[0,68,105,192],"widespread":[1],"adoption":[2],"of":[3,30,51,107,130,137,156,190],"large":[4],"language":[5],"models":[6,31,37,171],"(LLMs)":[7],"has":[8],"made":[9],"it":[10],"difficult":[11],"to":[12,33,62,149,202],"distinguish":[13],"human":[14,216],"writing":[15],"from":[16,166],"machine-produced":[17],"text":[18],"in":[19,92,128,208],"many":[20],"real":[21],"applications.":[22],"Detectors":[23],"that":[24,58,141,180],"were":[25],"effective":[26],"for":[27,78],"one":[28],"generation":[29],"tend":[32],"degrade":[34],"when":[35],"newer":[36],"or":[38],"modified":[39],"decoding":[40],"strategies":[41],"are":[42,110,119],"introduced.":[43],"In":[44],"this":[45,49,126],"work,":[46],"we":[47],"study":[48],"lack":[50],"stability":[52],"and":[53,89,95,116,133,139,154,175,187,210],"propose":[54],"a":[55,74,81,96,146,161],"hybrid":[56],"ensemble":[57,69,193],"is":[59,206,218],"explicitly":[60],"designed":[61],"cope":[63],"with":[64],"changing":[65],"generator":[66],"distributions.":[67],"combines":[70],"three":[71],"complementary":[72],"components:":[73],"RoBERTa-based":[75],"classifier":[76],"fine-tuned":[77],"supervised":[79],"detection,":[80],"curvature-inspired":[82],"score":[83],"based":[84],"on":[85,101,112,160,198],"perturbing":[86],"the":[87,113,117,142,152,181],"input":[88],"measuring":[90],"changes":[91],"model":[93,99],"likelihood,":[94],"compact":[97],"stylometric":[98],"built":[100],"hand-crafted":[102],"linguistic":[103],"features.":[104],"outputs":[106],"these":[108],"components":[109],"fused":[111],"probability":[114],"simplex,":[115],"weights":[118],"chosen":[120],"via":[121],"validation-based":[122],"search.":[123],"We":[124],"frame":[125],"approach":[127],"terms":[129],"variance":[131],"reduction":[132],"risk":[134],"under":[135],"mixtures":[136],"generators,":[138],"show":[140,179],"simplex":[143],"constraint":[144],"provides":[145],"simple":[147],"way":[148],"trade":[150],"off":[151],"strengths":[153],"weaknesses":[155],"each":[157],"branch.":[158],"Experiments":[159],"30000":[162],"document":[163],"corpus":[164],"drawn":[165],"several":[167],"LLM":[168],"families":[169],"including":[170],"unseen":[172],"during":[173],"training":[174],"paraphrased":[176],"attack":[177],"variants":[178],"proposed":[182],"method":[183],"achieves":[184],"94.2%":[185],"accuracy":[186],"an":[188],"AUC":[189],"0.978.":[191],"also":[194],"lowers":[195],"false":[196],"positives":[197],"scientific":[199],"articles":[200],"compared":[201],"strong":[203],"baselines,":[204],"which":[205],"critical":[207],"educational":[209],"research":[211],"settings":[212],"where":[213],"wrongly":[214],"flagging":[215],"work":[217],"costly":[219]},"counts_by_year":[],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-12-03T00:00:00"}