{"id":"https://openalex.org/W4387323716","doi":"https://doi.org/10.48550/arxiv.2310.00646","title":"Source Attribution for Large Language Model-Generated Data","display_name":"Source Attribution for Large Language Model-Generated Data","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4387323716","doi":"https://doi.org/10.48550/arxiv.2310.00646"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.00646","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00646","pdf_url":"https://arxiv.org/pdf/2310.00646","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.00646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104178151","display_name":"Jingtan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wang, Jingtan","raw_affiliation_strings":["School of Computing National University of Singapore Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101248249","display_name":"Xinyang Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lu, Xinyang","raw_affiliation_strings":["School of Computing National University of Singapore Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao, Zitong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhao, Zitong","raw_affiliation_strings":["School of Computing National University of Singapore Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064034052","display_name":"Zhongxiang Dai","orcid":"https://orcid.org/0000-0003-4963-6141","observed_orcids":["https://orcid.org/0000-0003-4963-6141"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dai, Zhongxiang","raw_affiliation_strings":["School of Computing National University of Singapore Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001103949","display_name":"Chuan-Sheng Foo","orcid":"https://orcid.org/0000-0002-4748-5792","observed_orcids":["https://orcid.org/0000-0002-4748-5792"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Foo, Chuan-Sheng","raw_affiliation_strings":["Institute for Infocomm Research Agency for Science , Technology and Research Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research Agency for Science , Technology and Research Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171111","display_name":"See-Kiong Ng","orcid":"https://orcid.org/0000-0001-6565-7511","observed_orcids":["https://orcid.org/0000-0001-6565-7511"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ng, See-Kiong","raw_affiliation_strings":["School of Computing National University of Singapore Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030304400","display_name":"Bryan Kian Hsiang Low","orcid":"https://orcid.org/0000-0003-2808-451X","observed_orcids":["https://orcid.org/0000-0003-2808-451X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Low, Bryan Kian Hsiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.6532999873161316,"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"}},"topics":[{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.6532999873161316,"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/T13851","display_name":"Law, AI, and Intellectual Property","score":0.11150000244379044,"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":0.0738999992609024,"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/source-attribution","display_name":"source attribution","score":0.9509999752044678},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.972000002861023},{"id":"https://openalex.org/keywords/watermarking","display_name":"watermarking","score":0.8100000023841858},{"id":"https://openalex.org/keywords/synthetic-text-generation","display_name":"synthetic text generation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/intellectual-property","display_name":"intellectual property","score":0.7799999713897705},{"id":"https://openalex.org/keywords/training-data","display_name":"training data","score":0.6800000071525574},{"id":"https://openalex.org/keywords/watermark-robustness","display_name":"watermark robustness","score":0.746999979019165},{"id":"https://openalex.org/keywords/data-provenance","display_name":"data provenance","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7766558527946472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289505004882812},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.6559849381446838},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.6030352115631104},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.5821039080619812},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5756951570510864},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5392832159996033},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5122305750846863},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4796172082424164},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.46043768525123596},{"id":"https://openalex.org/C2780625559","wikidata":"https://www.wikidata.org/wiki/Q5152592","display_name":"Commercialization","level":2,"score":0.44126880168914795},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3634229302406311},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29513171315193176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2367941439151764},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.22108057141304016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19962123036384583},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09784671664237976},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08308359980583191},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07588371634483337},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.00646","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00646","pdf_url":"https://arxiv.org/pdf/2310.00646","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.00646","doi":"https://doi.org/10.48550/arxiv.2310.00646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.00646","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.00646","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00646","pdf_url":"https://arxiv.org/pdf/2310.00646","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387323716.pdf","grobid_xml":"https://content.openalex.org/works/W4387323716.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412944613","https://openalex.org/W7165680490","https://openalex.org/W4387838318","https://openalex.org/W4415798785","https://openalex.org/W4412944319","https://openalex.org/W4403680773","https://openalex.org/W4400434905","https://openalex.org/W4409347910","https://openalex.org/W4409361276","https://openalex.org/W7222034441"],"abstract_inverted_index":{"The":[0],"impressive":[1],"performances":[2],"of":[3,25,41,73,116],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"and":[8,127],"their":[9,26,109],"immense":[10],"potential":[11],"for":[12,164],"commercialization":[13],"have":[14],"given":[15],"rise":[16],"to":[17,46,56,59,70,98,139,148,157],"serious":[18],"concerns":[19],"over":[20],"the":[21,31,39,42,48,65,71,113,154,162],"Intellectual":[22],"Property":[23],"(IP)":[24],"training":[27],"data.":[28],"In":[29,80],"particular,":[30],"synthetic":[32,75,100],"texts":[33,101,156],"generated":[34,155],"by":[35,63,77,91,94],"LLMs":[36],"may":[37],"infringe":[38],"IP":[40],"data":[43,66,158],"being":[44],"used":[45],"train":[47],"LLMs.":[49],"To":[50],"this":[51,81,86],"end,":[52],"it":[53],"is":[54],"imperative":[55],"be":[57,89],"able":[58],"perform":[60],"source":[61,121,130,166,177],"attribution":[62,122,131],"identifying":[64],"provider":[67],"who":[68],"contributed":[69],"generation":[72],"a":[74,129],"text":[76],"an":[78,96,146,150],"LLM.":[79],"paper,":[82],"we":[83],"show":[84,171],"that":[85,105,133,172],"problem":[87],"can":[88],"tackled":[90],"watermarking,":[92],"i.e.,":[93],"enabling":[95],"LLM":[97,147],"generate":[99],"with":[102],"embedded":[103],"watermarks":[104],"contain":[106],"information":[107],"about":[108],"source(s).":[110],"We":[111],"identify":[112],"key":[114,136],"properties":[115,137],"such":[117],"watermarking":[118],"frameworks":[119],"(e.g.,":[120],"accuracy,":[123],"robustness":[124],"against":[125],"adversaries),":[126],"propose":[128],"framework":[132,144,174],"satisfies":[134],"these":[135],"due":[138],"our":[140,173],"algorithmic":[141],"designs.":[142],"Our":[143],"enables":[145],"learn":[149],"accurate":[151],"mapping":[152],"from":[153],"providers,":[159],"which":[160],"sets":[161],"foundation":[163],"effective":[165,176],"attribution.":[167,178],"Extensive":[168],"empirical":[169],"evaluations":[170],"achieves":[175]},"counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2023-10-04T00:00:00"}