{"id":"https://openalex.org/W7160639714","doi":"https://doi.org/10.48550/arxiv.2605.05687","title":"DataDignity: Training Data Attribution for Large Language Models","display_name":"DataDignity: Training Data Attribution for Large Language Models","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160639714","doi":"https://doi.org/10.48550/arxiv.2605.05687"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05687","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.2605.05687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135712934","display_name":"Xiaomin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081559140","display_name":"Andrzej Banburski-Fahey","orcid":"https://orcid.org/0000-0002-3360-4121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Banburski-Fahey, Andrzej","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135662736","display_name":"Jaron Lanier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lanier, Jaron","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/T11948","display_name":"Machine Learning in Materials Science","score":0.24459999799728394,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.24459999799728394,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19009999930858612,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.1695999950170517,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6061000227928162},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.44029998779296875},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42320001125335693},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.3747999966144562},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942999958992004},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6061000227928162},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5770999789237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5090000033378601},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05687","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.2605.05687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05687","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Auditing":[0],"language-model":[1],"outputs":[2],"often":[3],"requires":[4,211],"more":[5],"than":[6],"judging":[7],"correctness:":[8],"an":[9],"auditor":[10],"may":[11],"need":[12],"to":[13,63,158],"identify":[14],"which":[15],"source":[16],"document":[17,121],"most":[18],"likely":[19],"supports":[20],"the":[21,44,49,154,199],"knowledge":[22],"expressed":[23],"in":[24],"a":[25,34,36,40,54,104,111,124],"response.":[26,50],"We":[27,51,99],"study":[28],"this":[29],"as":[30],"pinpoint":[31],"provenance:":[32],"given":[33],"prompt,":[35],"target-model":[37],"response,":[38],"and":[39,89,110,120,127,135,143,163],"candidate":[41],"corpus,":[42],"rank":[43],"documents":[45],"that":[46,81,178,206,214],"best":[47,200],"support":[48,218],"introduce":[52],"FakeWiki,":[53],"controlled":[55],"benchmark":[56],"of":[57],"3,537":[58],"fabricated":[59],"Wikipedia-style":[60],"articles":[61],"designed":[62],"preserve":[64],"ground-truth":[65],"provenance":[66,114],"while":[67,85],"weakening":[68],"lexical":[69,222],"shortcuts.":[70],"FakeWiki":[71],"includes":[72],"QA":[73],"probes,":[74],"source-preserving":[75],"paraphrases,":[76],"retro-generated":[77],"variants,":[78],"hard":[79],"anti-documents":[80],"remain":[82],"topically":[83],"similar":[84],"removing":[86],"answer-critical":[87],"facts,":[88],"five":[90,144],"query":[91,145],"conditions:":[92],"clean":[93],"prompting":[94],"plus":[95],"four":[96],"jailbreak-inspired":[97,187],"transformations.":[98],"evaluate":[100],"seven":[101],"retrieval":[102,156],"baselines,":[103],"training-free":[105],"activation-steering":[106],"retrieval-fusion":[107],"method,":[108],"SteerFuse,":[109],"supervised":[112,175],"contrastive":[113],"ranker,":[115],"ScoringModel.":[116],"ScoringModel":[117,147,190],"maps":[118],"response":[119],"features":[122],"into":[123],"shared":[125],"space":[126],"is":[128,169],"trained":[129],"with":[130],"InfoNCE":[131],"using":[132],"in-batch,":[133],"retrieval-mined,":[134],"anti-document":[136],"negatives.":[137],"Across":[138],"nine":[139],"open-weight":[140],"instruction-tuned":[141],"LLMs":[142],"conditions,":[146],"improves":[148,191],"mean":[149],"Recall@10":[150,192],"from":[151,219],"35.0":[152],"for":[153],"strongest":[155],"baseline":[157],"52.2,":[159],"without":[160],"inference-time":[161],"fusion,":[162],"wins":[164],"41/45":[165],"model-by-condition":[166],"cells.":[167],"SteerFuse":[168],"usually":[170],"second-best":[171],"despite":[172],"requiring":[173],"no":[174],"training,":[176],"showing":[177],"activation-space":[179],"evidence":[180],"can":[181],"efficiently":[182],"complement":[183],"text":[184],"retrieval.":[185],"On":[186],"transformed":[188],"queries,":[189],"by":[193],"15.7":[194],"points":[195],"on":[196],"average":[197],"over":[198],"baseline.":[201],"Overall,":[202],"our":[203],"work":[204],"shows":[205],"robust":[207],"training":[208],"data":[209],"attribution":[210],"evaluation":[212],"settings":[213],"separate":[215],"true":[216],"answer":[217],"topical":[220],"or":[221],"resemblance.":[223]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}