{"id":"https://openalex.org/W4417097604","doi":"https://doi.org/10.18653/v1/2026.findings-acl.353","title":"Hey, That\u2019s My Data! Token-Only Dataset Inference in Large Language Models","display_name":"Hey, That\u2019s My Data! Token-Only Dataset Inference in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417097604","doi":"https://doi.org/10.18653/v1/2026.findings-acl.353"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.353","pdf_url":"https://aclanthology.org/2026.findings-acl.353.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.353.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100770694","display_name":"Xiong Chen","orcid":"https://orcid.org/0000-0003-0855-4764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080917748","display_name":"Zihao Wang","orcid":"https://orcid.org/0009-0008-7065-4751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000660323","display_name":"Rui Zhu","orcid":"https://orcid.org/0009-0003-1280-169X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081990594","display_name":"Jingwei Xiong","orcid":"https://orcid.org/0000-0003-2667-4233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwei Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078007096","display_name":"Haixu Tang","orcid":"https://orcid.org/0000-0001-8963-8155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haixu Tang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03234508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7105","last_page":"7120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.39959999918937683,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.39959999918937683,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11829999834299088,"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":0.05979999899864197,"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/safeguarding","display_name":"Safeguarding","score":0.6428999900817871},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5339000225067139},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44850000739097595},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44670000672340393},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935999989509583},{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.6428999900817871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43160000443458557},{"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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C59577422","wikidata":"https://www.wikidata.org/wiki/Q10265143","display_name":"False accusation","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.353","pdf_url":"https://aclanthology.org/2026.findings-acl.353.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.06057","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.06057","pdf_url":"https://arxiv.org/pdf/2506.06057","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:2506.06057","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.06057","pdf_url":"https://arxiv.org/pdf/2506.06057","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.06057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.06057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:10.18653/v1/2026.findings-acl.353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.353","pdf_url":"https://aclanthology.org/2026.findings-acl.353.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417097604.pdf","grobid_xml":"https://content.openalex.org/works/W4417097604.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"rely":[4],"on":[5,54,64,69,82,105],"massive":[6],"training":[7,74],"datasets,":[8],"often":[9],"including":[10],"proprietary":[11,123],"data,":[12],"which":[13],"raises":[14],"concerns":[15],"about":[16],"unauthorized":[17],"usage":[18],"and":[19,108],"copyright":[20],"infringement.Existing":[21],"dataset":[22,50,100],"inference":[23,44,51],"methods":[24],"typically":[25],"require":[26],"access":[27],"to":[28,96],"log":[29],"probabilities":[30],"or":[31],"other":[32],"internal":[33],"signals,":[34],"but":[35],"many":[36],"modern":[37],"LLMs":[38,110],"restrict":[39],"such":[40],"access,":[41,118],"motivating":[42],"token-only":[43,49],"approaches.We":[45],"propose":[46],"CatShift,":[47],"a":[48,70,91,99],"framework":[52],"based":[53],"catastrophic":[55],"forgetting,":[56],"where":[57],"models":[58],"overwrite":[59],"prior":[60],"knowledge":[61],"when":[62],"trained":[63],"new":[65],"data.Fine-tuning":[66],"an":[67],"LLM":[68],"subset":[71],"of":[72,122],"its":[73],"data":[75],"induces":[76],"larger":[77],"output":[78],"shifts":[79,87],"than":[80],"finetuning":[81],"unseen":[83],"data.CatShift":[84],"compares":[85],"these":[86],"against":[88],"those":[89],"from":[90],"known":[92],"non-member":[93],"validation":[94],"set":[95],"infer":[97],"whether":[98],"was":[101],"included":[102],"in":[103],"training.Experiments":[104],"both":[106],"opensource":[107],"API-based":[109],"show":[111],"that":[112],"CatShift":[113],"remains":[114],"effective":[115],"without":[116],"logit":[117],"enabling":[119],"practical":[120],"protection":[121],"datasets.":[124]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}