{"id":"https://openalex.org/W7104956559","doi":"https://doi.org/10.48550/arxiv.2511.06645","title":"Adaptive Testing for Segmenting Watermarked Texts From Language Models","display_name":"Adaptive Testing for Segmenting Watermarked Texts From Language Models","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7104956559","doi":"https://doi.org/10.48550/arxiv.2511.06645"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.06645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06645","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.06645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Xingchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xingchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Xiaochi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaochi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Li, Guanxun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guanxun","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":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/T10028","display_name":"Topic Modeling","score":0.21649999916553497,"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/T10028","display_name":"Topic Modeling","score":0.21649999916553497,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.12449999898672104,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.07769999653100967,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/segmentation","display_name":"Segmentation","score":0.6190000176429749},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.5645999908447266},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.5063999891281128},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45719999074935913},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3783999979496002},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6743999719619751},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6190000176429749},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.5063999891281128},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3783999979496002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.06645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06645","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.06645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06645","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8893710374832153}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"adoption":[2],"of":[3,28,68,105,129,169],"large":[4],"language":[5],"models":[6],"(LLMs),":[7],"such":[8],"as":[9],"GPT-4":[10],"and":[11,30,78,112,160,171],"Claude":[12],"3.5,":[13],"underscores":[14],"the":[15,26,42,63,84,101,118,143,154],"need":[16,144],"to":[17,24,37,53,83,99,117,136],"distinguish":[18],"LLM-generated":[19,51],"text":[20,52,109],"from":[21],"human-written":[22],"content":[23],"mitigate":[25],"spread":[27],"misinformation":[29],"misuse":[31],"in":[32,120,162],"education.":[33],"One":[34],"promising":[35],"approach":[36,82,119],"address":[38],"this":[39,58,81,95],"issue":[40],"is":[41,157],"watermark":[43,91],"technique,":[44],"which":[45,124],"embeds":[46],"subtle":[47],"statistical":[48],"signals":[49],"into":[50,110],"enable":[54],"reliable":[55],"identification.":[56],"In":[57,115],"paper,":[59],"we":[60,93],"first":[61],"generalize":[62],"likelihood-based":[64],"LLM":[65],"detection":[66,97],"method":[67],"a":[69,74,107,121,167],"previous":[70,122],"study":[71],"by":[72],"introducing":[73],"flexible":[75],"weighted":[76],"formulation,":[77],"further":[79],"adapt":[80],"inverse":[85],"transform":[86],"sampling":[87],"method.":[88],"Moving":[89],"beyond":[90],"detection,":[92],"extend":[94],"adaptive":[96],"strategy":[98],"tackle":[100],"more":[102],"challenging":[103],"problem":[104],"segmenting":[106,164],"given":[108],"watermarked":[111,170],"non-watermarked":[113,172],"substrings.":[114],"contrast":[116],"study,":[123],"relies":[125],"on":[126],"accurate":[127],"estimation":[128],"next-token":[130],"probabilities":[131],"that":[132,153],"are":[133],"highly":[134],"sensitive":[135],"prompt":[137,147],"estimation,":[138],"our":[139],"proposed":[140,155],"framework":[141],"removes":[142],"for":[145],"precise":[146],"estimation.":[148],"Extensive":[149],"numerical":[150],"experiments":[151],"demonstrate":[152],"methodology":[156],"both":[158],"effective":[159],"robust":[161],"accurately":[163],"texts":[165],"containing":[166],"mixture":[168],"content.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-11-12T00:00:00"}