{"id":"https://openalex.org/W4416034243","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1004","title":"SENTRA: Selected-Next-Token Transformer for LLM Text Detection","display_name":"SENTRA: Selected-Next-Token Transformer for LLM Text Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034243","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1004"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1004","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1004.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.1004.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308522","display_name":"Mitchell Plyler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116574","display_name":"Mo Sci Corporation (United States)","ror":"https://ror.org/02bwppq44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116574"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell Plyler","raw_affiliation_strings":["Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report","institution_ids":["https://openalex.org/I4210116574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116568560","display_name":"Yilun Zhang","orcid":"https://orcid.org/0009-0001-8471-6983"},"institutions":[{"id":"https://openalex.org/I4210116574","display_name":"Mo Sci Corporation (United States)","ror":"https://ror.org/02bwppq44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116574"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilun Zhang","raw_affiliation_strings":["Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report","institution_ids":["https://openalex.org/I4210116574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016384155","display_name":"Alexander Tuzhilin","orcid":"https://orcid.org/0000-0003-3354-8462"},"institutions":[{"id":"https://openalex.org/I4210116574","display_name":"Mo Sci Corporation (United States)","ror":"https://ror.org/02bwppq44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116574"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Tuzhilin","raw_affiliation_strings":["Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report","institution_ids":["https://openalex.org/I4210116574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308523","display_name":"Saoud Khalifah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116574","display_name":"Mo Sci Corporation (United States)","ror":"https://ror.org/02bwppq44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116574"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saoud Khalifah","raw_affiliation_strings":["Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report","institution_ids":["https://openalex.org/I4210116574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041081630","display_name":"Sen Tian","orcid":"https://orcid.org/0000-0002-6486-3142"},"institutions":[{"id":"https://openalex.org/I4210116574","display_name":"Mo Sci Corporation (United States)","ror":"https://ror.org/02bwppq44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116574"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Tian","raw_affiliation_strings":["Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mozilla Corporation Mozilla Corporation New York University System Card. Technical Report","institution_ids":["https://openalex.org/I4210116574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116574"],"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":"18499","last_page":"18516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.2434999942779541,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.2434999942779541,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.195700004696846,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.11860000342130661,"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/transformer","display_name":"Transformer","score":0.39239999651908875},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.2736000120639801},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27250000834465027},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.26600000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5019000172615051},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30149999260902405},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.26429998874664307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1004","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1004.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.1004","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1004","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1004.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034243.pdf","grobid_xml":"https://content.openalex.org/works/W4416034243.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0],"are":[1],"becoming":[2],"increasingly":[3],"capable":[4],"and":[5,9,38,53],"widespread.Consequently,":[6],"the":[7,21,86],"potential":[8],"reality":[10],"of":[11,23,60,72],"their":[12],"misuse":[13],"is":[14,28,46,76],"also":[15],"growing.In":[16],"this":[17],"work,":[18],"we":[19],"address":[20],"problem":[22],"detecting":[24],"LLM-generated":[25],"text":[26,41,73],"that":[27,80],"not":[29],"explicitly":[30],"declared":[31],"as":[32],"such.We":[33],"present":[34],"a":[35,47,77],"novel,":[36],"generalpurpose,":[37],"supervised":[39],"LLM":[40],"detector,":[42],"SElected-Next-Token":[43],"tRAnsformer":[44],"(SENTRA).SENTRA":[45],"Transformer-based":[48],"encoder":[49],"leveraging":[50],"selected-next-token-probability":[51],"sequences":[52],"utilizing":[54],"contrastive":[55],"pre-training":[56],"on":[57,64],"large":[58],"amounts":[59],"unlabeled":[61],"data.Our":[62],"experiments":[63],"three":[65],"popular":[66,83],"public":[67],"datasets":[68],"across":[69],"24":[70],"domains":[71],"demonstrate":[74],"SENTRA":[75],"general-purpose":[78],"classifier":[79],"significantly":[81],"outperforms":[82],"baselines":[84],"in":[85],"out-ofdomain":[87],"setting.":[88]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}