{"id":"https://openalex.org/W4412888000","doi":"https://doi.org/10.18653/v1/2025.findings-acl.791","title":"FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Models","display_name":"FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888000","doi":"https://doi.org/10.18653/v1/2025.findings-acl.791"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.791","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.791","pdf_url":"https://aclanthology.org/2025.findings-acl.791.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.791.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028062574","display_name":"Yaxin Du","orcid":"https://orcid.org/0000-0001-7153-5924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxin Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728765","display_name":"Rui Ye","orcid":"https://orcid.org/0000-0002-9924-937X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114336417","display_name":"Fengting Yuchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengting Yuchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102517632","display_name":"Wanru Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanru Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873727","display_name":"Jingjing Qu","orcid":"https://orcid.org/0000-0002-8510-433X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645703","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0001-7873-6577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066373402","display_name":"Siheng Chen","orcid":"https://orcid.org/0000-0002-9144-0583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siheng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93055762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"15267","last_page":"15291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9381999969482422,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9381999969482422,"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/T11719","display_name":"Data Quality and Management","score":0.9187999963760376,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/computer-science","display_name":"Computer science","score":0.8137286901473999},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.677358090877533},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.6500636339187622},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4254128932952881},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2712705731391907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22044941782951355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137286901473999},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.677358090877533},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6500636339187622},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4254128932952881},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2712705731391907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22044941782951355},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.791","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.791","pdf_url":"https://aclanthology.org/2025.findings-acl.791.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.791","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.791","pdf_url":"https://aclanthology.org/2025.findings-acl.791.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888000.pdf","grobid_xml":"https://content.openalex.org/works/W4412888000.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384667405","https://openalex.org/W2389266787","https://openalex.org/W2363885542","https://openalex.org/W2387206255","https://openalex.org/W2355570285","https://openalex.org/W2364958354","https://openalex.org/W2352797113","https://openalex.org/W2372137583","https://openalex.org/W2374872591","https://openalex.org/W1548050717"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"enables":[3],"privacypreserving":[4],"collaborative":[5,117],"instruction":[6,50],"tuning":[7,51],"of":[8,21],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"by":[13],"leveraging":[14],"massively":[15],"distributed":[16],"data.However,":[17],"the":[18,91,106,133,177,204],"decentralized":[19],"nature":[20],"FL":[22,102],"exacerbates":[23],"data":[24,55,81,114,123,152],"quality":[25,56,72,124],"challenges,":[26],"as":[27],"local":[28],"clients":[29],"lack":[30],"global":[31],"visibility":[32],"to":[33,83],"filter":[34],"noisy":[35],"or":[36],"low-quality":[37],"samples":[38],"before":[39],"training.To":[40],"resolve":[41],"this":[42],"issue,":[43],"we":[44,63,97],"propose":[45,64],"FedDQC,":[46],"a":[47,99,116],"novel":[48],"federated":[49],"framework":[52,119],"with":[53],"dynamic":[54,130],"control.Our":[57],"approach":[58],"introduces":[59],"two":[60],"key":[61],"innovations.First,":[62],"instruction-response":[65],"alignment":[66],"(IRA)-an":[67],"efficient":[68],"client-side":[69],"metric":[70],"for":[71,164,172,191,199],"evaluation":[73],"requiring":[74],"only":[75],"lowcost":[76],"inference.We":[77],"validate":[78],"that":[79,143],"higher-IRA":[80],"corresponds":[82],"more":[84,168,195],"relevant":[85],"and":[86,139],"easierto-learn":[87],"question-answer":[88],"pairs.Second,":[89],"mirroring":[90],"human":[92],"easy-to-hard":[93],"knowledge":[94],"acquisition":[95],"process,":[96],"design":[98],"quality-aware":[100],"hierarchical":[101],"training":[103,134],"framework,":[104],"where":[105],"LLM":[107,148],"is":[108,155],"progressively":[109],"fine-tuned":[110],"from":[111],"highto":[112],"low-IRA":[113],"in":[115,153,157],"manner.The":[118],"also":[120],"supports":[121],"adaptive":[122],"assessment":[125],"at":[126],"each":[127],"hierarchy,":[128],"enabling":[129],"adjustments":[131],"throughout":[132],"process.Extensive":[135],"experiments":[136],"on":[137,150],"synthetic":[138],"real-world":[140],"datasets":[141],"show":[142],"our":[144],"method":[145],"significantly":[146],"improves":[147],"performance":[149],"mixed-quality":[151],"FL.Code":[154],"available":[156],"https://github.com/DorothyDUUU/FedDQC.":[158],"Q:":[159],"1000":[160,187],"men":[161,169,188,196],"have":[162,189],"provisions":[163,178,190,205],"15":[165,192],"days.If":[166,193],"200":[167,194],"join":[170,197],"them,":[171,198],"how":[173,200],"many":[174,201],"days":[175,202],"will":[176,203],"last":[179,206],"now?A:":[180],"100015":[181],"=":[182,185,208,211],"1200x,":[183,209],"x":[184,210],"12":[186],"now?100015":[207],"12.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}