{"id":"https://openalex.org/W7140109918","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.56","title":"DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization","display_name":"DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140109918","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.56"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.56","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.56","pdf_url":"https://aclanthology.org/2026.findings-eacl.56.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.56.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146906850","display_name":"Haiyang Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Shen","raw_affiliation_strings":["Institute for Artificial Intelligence , Peking University","School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146787429","display_name":"Hang Yan","orcid":null,"observed_orcids":[]},"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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hang Yan","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120696062","display_name":"Zhongshi Xing","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongshi Xing","raw_affiliation_strings":["School of Computer Science , Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104285228","display_name":"Mugeng Liu","orcid":"https://orcid.org/0009-0002-7625-8721","observed_orcids":["https://orcid.org/0009-0002-7625-8721"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mugeng Liu","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146829687","display_name":"Yue Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["School of Software & Microelectronics , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software & Microelectronics , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146820135","display_name":"Zhiyang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Chen","raw_affiliation_strings":["Institute for Artificial Intelligence , Peking University","School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146699289","display_name":"Yuxiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Wang","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136712999","display_name":"Jiuzheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuzheng Wang","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146598187","display_name":"Yun Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Ma","raw_affiliation_strings":["Institute for Artificial Intelligence , Peking University","School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.5469,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95045857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1065","last_page":"1078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5874000191688538,"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/T10028","display_name":"Topic Modeling","score":0.5874000191688538,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4041000008583069,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0008999999845400453,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9869999885559082},{"id":"https://openalex.org/keywords/domain-specific-retrieval","display_name":"domain-specific retrieval","score":0.878000020980835},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.8980000019073486},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5472000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.56","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.56","pdf_url":"https://aclanthology.org/2026.findings-eacl.56.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.10989","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10989","pdf_url":"https://arxiv.org/pdf/2505.10989","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.10989","doi":"https://doi.org/10.48550/arxiv.2505.10989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.10989","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.56","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.56","pdf_url":"https://aclanthology.org/2026.findings-eacl.56.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140109918.pdf","grobid_xml":"https://content.openalex.org/works/W7140109918.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416249945","https://openalex.org/W4404781771","https://openalex.org/W4404308464","https://openalex.org/W4411119833","https://openalex.org/W4415191111","https://openalex.org/W7166871976","https://openalex.org/W4398794878","https://openalex.org/W4413374917","https://openalex.org/W7138930052","https://openalex.org/W7208723464"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"can":[3],"substantially":[4],"enhance":[5],"the":[6],"performance":[7,67,74,129],"of":[8,97],"LLMs":[9],"on":[10,21,30,75,124],"knowledge-intensive":[11],"tasks.Various":[12],"RAG":[13,73,147],"paradigms-including":[14],"vanilla,":[15,143],"planningbased,":[16,144],"and":[17,33,68,92,101,113,131,145],"iterative":[18,146],"RAG-all":[19],"depend":[20],"a":[22,47,51,56,81,94,107],"robust":[23],"retriever,":[24],"yet":[25],"existing":[26],"retrievers":[27,122,139],"rely":[28],"heavily":[29],"public":[31],"knowledge":[32],"often":[34],"falter":[35],"when":[36,136],"faced":[37],"with":[38,55],"domain-specific":[39,65,76,85],"queries.To":[40],"address":[41],"these":[42],"limitations,":[43],"we":[44,78,105,149],"introduce":[45],"DRAGON,":[46,104],"framework":[48],"that":[49,121],"combines":[50],"data-construction":[52],"modeling":[53],"approach":[54],"scalable":[57],"synthetic":[58,109],"data-generation":[59],"pipeline,":[60],"specifically":[61],"designed":[62],"to":[63],"optimize":[64],"retrieval":[66],"bolster":[69],"retriever":[70,117],"robustness.To":[71],"evaluate":[72],"RAGs,":[77],"propose":[79],"DRAGONBENCH,":[80],"benchmark":[82],"spanning":[83],"8":[84],"document":[86],"collections":[87],"across":[88],"4":[89],"distinct":[90],"fields":[91],"featuring":[93],"wide":[95],"spectrum":[96],"query":[98],"complexities,":[99],"answerability,":[100],"hop":[102],"numbers.Leveraging":[103],"generate":[106],"large-scale":[108],"dataset-encompassing":[110],"both":[111],"single-hop":[112],"multi-hop":[114],"queries-to":[115],"enrich":[116],"training.Extensive":[118],"experiments":[119],"demonstrate":[120],"trained":[123],"this":[125],"data":[126],"yield":[127],"significant":[128],"gains":[130],"exhibit":[132],"strong":[133],"cross-domain":[134],"generalization.Moreover,":[135],"our":[137],"optimized":[138],"are":[140],"integrated":[141],"into":[142],"paradigms,":[148],"observe":[150],"consistent":[151],"end-to-end":[152],"improvements":[153],"in":[154],"system":[155],"accuracy.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-02-12T00:00:00"}