{"id":"https://openalex.org/W4416034840","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.609","title":"How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study","display_name":"How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034840","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.609"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.609","pdf_url":"https://aclanthology.org/2025.findings-emnlp.609.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.609.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111381708","display_name":"Matthieu Dubois","orcid":null},"institutions":[{"id":"https://openalex.org/I4403928267","display_name":"International Laboratory on Learning Systems","ror":"https://ror.org/02bkw1m29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210164802","https://openalex.org/I4403928267","https://openalex.org/I49663120","https://openalex.org/I5023651","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthieu Dubois","raw_affiliation_strings":["ILLS - International Laboratory on Learning Systems (Montr\u00e9al - Canada)","MLIA - Machine Learning and Information Access (Tour 65-66 3\u00e8me \u00e9tage\r\n4, place Jussieu\r\n75005 Paris \u2013 France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILLS - International Laboratory on Learning Systems (Montr\u00e9al - Canada)","institution_ids":["https://openalex.org/I4403928267"]},{"raw_affiliation_string":"MLIA - Machine Learning and Information Access (Tour 65-66 3\u00e8me \u00e9tage\r\n4, place Jussieu\r\n75005 Paris \u2013 France - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030615769","display_name":"Fran\u00e7ois Yvon","orcid":"https://orcid.org/0000-0002-7972-7442"},"institutions":[{"id":"https://openalex.org/I4403928267","display_name":"International Laboratory on Learning Systems","ror":"https://ror.org/02bkw1m29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210164802","https://openalex.org/I4403928267","https://openalex.org/I49663120","https://openalex.org/I5023651","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Yvon","raw_affiliation_strings":["ILLS - International Laboratory on Learning Systems (Montr\u00e9al - Canada)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILLS - International Laboratory on Learning Systems (Montr\u00e9al - Canada)","institution_ids":["https://openalex.org/I4403928267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071189599","display_name":"Pablo Piantanida","orcid":"https://orcid.org/0000-0002-8717-2117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Piantanida","raw_affiliation_strings":["MLIA - Machine Learning and Information Access (Tour 65-66 3\u00e8me \u00e9tage\r\n4, place Jussieu\r\n75005 Paris \u2013 France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MLIA - Machine Learning and Information Access (Tour 65-66 3\u00e8me \u00e9tage\r\n4, place Jussieu\r\n75005 Paris \u2013 France - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"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":"11369","last_page":"11387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.2214999943971634,"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":0.2214999943971634,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.05220000073313713,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.047600001096725464,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3303999900817871},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2492000013589859}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4797999858856201},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.391400009393692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36579999327659607},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27219998836517334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.2662999927997589},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2492000013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23309999704360962}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.609","pdf_url":"https://aclanthology.org/2025.findings-emnlp.609.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"},{"id":"pmh:oai:HAL:hal-05354580v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05354580","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2025, Suzhou, China, China. ⟨10.18653/v1/2025.findings-emnlp.609⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.609","pdf_url":"https://aclanthology.org/2025.findings-emnlp.609.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/W4416034840.pdf","grobid_xml":"https://content.openalex.org/works/W4416034840.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"texts":[1],"generated":[2],"by":[3],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"are":[8,54],"ever":[9],"more":[10,130],"common":[11],"and":[12,125,150],"often":[13,32],"indistinguishable":[14],"from":[15,108],"human-written":[16],"content,":[17],"research":[18],"on":[19,73],"automatic":[20],"text":[21],"detection":[22,83,123],"has":[23],"attracted":[24],"growing":[25],"attention.Many":[26],"recent":[27],"detectors":[28],"report":[29],"near-perfect":[30,109],"accuracy,":[31,104],"boasting":[33],"AUROC":[34,106],"scores":[35],"above":[36],"99%.However,":[37],"these":[38],"claims":[39],"typically":[40],"assume":[41],"fixed":[42],"generation":[43],"settings,":[44],"leaving":[45],"open":[46],"the":[47,127],"question":[48],"of":[49],"how":[50,65,74],"robust":[51],"such":[52],"systems":[53],"to":[55,90,111],"changes":[56],"in":[57,77,113,121],"decoding":[58,67,91,144],"strategies.In":[59],"this":[60],"work,":[61],"we":[62,137],"systematically":[63],"examine":[64],"sampling-based":[66],"impacts":[68],"detectability,":[69],"with":[70,105,147],"a":[71,78,139],"focus":[72],"subtle":[75],"variations":[76],"model's":[79],"(sub)word-level":[80],"distribution":[81],"affect":[82],"performance.We":[84],"find":[85],"that":[86],"even":[87],"minor":[88],"adjustments":[89],"parameters":[92],"-such":[93],"as":[94],"temperature,":[95],"top-p,":[96],"or":[97],"nucleus":[98],"sampling":[99],"-can":[100],"severely":[101],"impair":[102],"detector":[103],"dropping":[107],"levels":[110],"1%":[112],"some":[114],"settings.Our":[115],"findings":[116],"expose":[117],"critical":[118],"blind":[119],"spots":[120],"current":[122],"methods":[124],"emphasize":[126],"need":[128],"for":[129],"comprehensive":[131],"evaluation":[132,151],"protocols.To":[133],"facilitate":[134],"future":[135],"research,":[136],"release":[138],"large-scale":[140],"dataset":[141],"encompassing":[142],"37":[143],"configurations,":[145],"along":[146],"our":[148],"code":[149],"framework":[152],"https://github.com/":[153],"BaggerOfWords/Sampling-and-Detection.":[154]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-11-08T00:00:00"}