{"id":"https://openalex.org/W7166871976","doi":"https://doi.org/10.18653/v1/2026.findings-acl.960","title":"Domain-Specific Data Generation Framework for RAG Adaptation","display_name":"Domain-Specific Data Generation Framework for RAG Adaptation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166871976","doi":"https://doi.org/10.18653/v1/2026.findings-acl.960"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.960","pdf_url":"https://aclanthology.org/2026.findings-acl.960.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.960.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084858586","display_name":"Chris Xing Tian","orcid":"https://orcid.org/0000-0002-6709-0261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Xing Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139739453","display_name":"Weihao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihao Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139807332","display_name":"Zhen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791441","display_name":"Hui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139775926","display_name":"Zhengyuan Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyuan Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834850","display_name":"Haoliang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoliang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139731878","display_name":"Shiqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siwei Ma","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86043728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19236","last_page":"19250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12189999967813492,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12189999967813492,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.030700000002980232,"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/T12031","display_name":"Speech and dialogue systems","score":0.023900000378489494,"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/adaptation","display_name":"Adaptation (eye)","score":0.3172000050544739},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.243599995970726},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.24210000038146973},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2410999983549118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5885999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968999981880188},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.243599995970726},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.24210000038146973},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2410999983549118},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.24070000648498535},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23810000717639923}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.960","pdf_url":"https://aclanthology.org/2026.findings-acl.960.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.960","pdf_url":"https://aclanthology.org/2026.findings-acl.960.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166871976.pdf","grobid_xml":"https://content.openalex.org/works/W7166871976.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"combines":[3],"the":[4],"language":[5,12],"understanding":[6],"and":[7,42,82,107,127,141],"reasoning":[8],"capabilities":[9],"of":[10,79,85],"large":[11,140],"models":[13,81],"(LLMs)":[14],"with":[15,110],"external":[16],"retrieval":[17],"to":[18,25,53,131],"produce":[19],"domain-grounded":[20,48],"responses.Effectively":[21],"adapting":[22],"RAG":[23,55,66],"systems":[24],"domain-specific":[26],"settings":[27],"requires":[28],"specialized,":[29],"context-rich":[30],"training":[31,62],"data":[32],"beyond":[33],"general-purpose":[34],"questionanswering":[35],"datasets.Here,":[36],"we":[37,72],"propose":[38],"RA-Gen,":[39],"a":[40],"scalable":[41],"modular":[43,117],"data-centric":[44],"framework":[45],"for":[46,64,76,135,152],"generating":[47],"question-answer-context":[49],"(QAC)":[50],"triples":[51,59,92],"tailored":[52],"diverse":[54,100],"adaptation":[56,67],"strategies.These":[57],"QAC":[58,91],"serve":[60],"as":[61],"signals":[63],"multiple":[65],"approaches;":[68],"in":[69],"this":[70],"work,":[71],"demonstrate":[73],"their":[74],"use":[75],"contrastive":[77],"finetuning":[78],"embedding":[80],"supervised":[83],"fine-tuning":[84],"LLMs":[86],"under":[87],"retrieved":[88],"contexts.RAGen":[89],"generates":[90],"by":[93,103],"identifying":[94],"key":[95],"concepts":[96],"within":[97],"documents,":[98],"producing":[99],"questions":[101],"guided":[102],"Bloom's":[104],"Taxonomy-inspired":[105],"principles,":[106],"pairing":[108],"them":[109],"precise":[111],"answers":[112],"extracted":[113],"from":[114],"relevant":[115],"contexts.Its":[116],"pipeline":[118],"incorporates":[119],"semantic":[120],"chunking,":[121],"hierarchical":[122],"concept":[123],"extraction,":[124],"multi-chunk":[125],"retrieval,":[126],"curated":[128],"distractor":[129],"contexts":[130],"encourage":[132],"robust":[133],"reasoning.Designed":[134],"scalability,":[136],"RAGen":[137],"efficiently":[138],"handles":[139],"evolving":[142],"document":[143],"corpora":[144],"without":[145],"redundant":[146],"processing,":[147],"making":[148],"it":[149],"particularly":[150],"suitable":[151],"dynamic":[153],"domains":[154],"like":[155],"enterprise":[156],"knowledge":[157],"bases.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}