{"id":"https://openalex.org/W7166809149","doi":"https://doi.org/10.18653/v1/2026.acl-long.435","title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","display_name":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809149","doi":"https://doi.org/10.18653/v1/2026.acl-long.435"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.435","doi":"https://doi.org/10.18653/v1/2026.acl-long.435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.435","pdf_url":"https://aclanthology.org/2026.acl-long.435.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.435.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100345753","display_name":"Yu Li","orcid":"https://orcid.org/0000-0002-3664-6722","observed_orcids":["https://orcid.org/0000-0002-3664-6722","https://orcid.org/0000-0003-1865-8276","https://orcid.org/0009-0001-4705-049X"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139858389","display_name":"Xiaoran Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Shang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139829912","display_name":"Qizhi Pei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhi Pei","raw_affiliation_strings":["Renmin University of China","Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735266","display_name":"Yun Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734962","display_name":"Xin Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Gao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139802220","display_name":"Honglin Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglin Lin","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771958","display_name":"Zhanping Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanping Zhong","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847329","display_name":"Zhuoshi Pan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoshi Pan","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466","observed_orcids":["https://orcid.org/0000-0001-7765-8466","https://orcid.org/0009-0006-1277-0493","https://orcid.org/0000-0003-3437-2630"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727027","display_name":"Xiaoyang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736183","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X","observed_orcids":["https://orcid.org/0000-0001-8697-695X"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896","observed_orcids":["https://orcid.org/0000-0002-8865-7896"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827652","display_name":"Feng Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhao","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139745386","display_name":"Lijun Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.4360479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9606","last_page":"9625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.22020000219345093,"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":0.22020000219345093,"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":0.17810000479221344,"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":0.14900000393390656,"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/data-lineage","display_name":"data lineage","score":0.9449999928474426},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7900000214576721},{"id":"https://openalex.org/keywords/post-training","display_name":"post-training","score":0.7269999980926514},{"id":"https://openalex.org/keywords/multi-agent-framework","display_name":"multi-agent framework","score":0.871999979019165},{"id":"https://openalex.org/keywords/provenance-tracking","display_name":"provenance tracking","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4090999960899353},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.33309999108314514},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3319999873638153},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3100000023841858},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.435","doi":"https://doi.org/10.18653/v1/2026.acl-long.435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.435","pdf_url":"https://aclanthology.org/2026.acl-long.435.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.435","doi":"https://doi.org/10.18653/v1/2026.acl-long.435","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.435","pdf_url":"https://aclanthology.org/2026.acl-long.435.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.82193523645401,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G179212483","display_name":null,"funder_award_id":"2108085UD12","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809149.pdf","grobid_xml":"https://content.openalex.org/works/W7166809149.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223035252","https://openalex.org/W4385570455","https://openalex.org/W4412944754","https://openalex.org/W7137845081","https://openalex.org/W7166848025","https://openalex.org/W4412887063","https://openalex.org/W4416236279","https://openalex.org/W7160553872","https://openalex.org/W7166878630","https://openalex.org/W4412889719"],"abstract_inverted_index":{"Yu":[0],"Li,":[1],"Xiaoran":[2],"Shang,":[3],"Qizhi":[4],"Pei,":[5],"Yun":[6],"Zhu,":[7],"Xin":[8],"Gao,":[9],"Honglin":[10],"Lin,":[11,23],"Zhanping":[12],"Zhong,":[13],"Zhuoshi":[14],"Pan,":[15],"Zheng":[16],"Liu,":[17],"Xiaoyang":[18],"Wang,":[19],"Conghui":[20],"He,":[21],"Dahua":[22],"Feng":[24],"Zhao,":[25],"Lijun":[26],"Wu.":[27],"Proceedings":[28],"of":[29,34],"the":[30,35],"64th":[31],"Annual":[32],"Meeting":[33],"Association":[36],"for":[37],"Computational":[38],"Linguistics":[39],"(Volume":[40],"1:":[41],"Long":[42],"Papers).":[43],"2026.":[44]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}
