{"id":"https://openalex.org/W7140140937","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.176","title":"DS2-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning","display_name":"DS2-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140140937","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.176"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.176","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.176","pdf_url":"https://aclanthology.org/2026.findings-eacl.176.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.176.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113407873","display_name":"Ruiyao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiyao Xu","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048727099","display_name":"Noelle I. Samia","orcid":"https://orcid.org/0000-0002-8644-4192","observed_orcids":["https://orcid.org/0000-0002-8644-4192"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noelle I. Samia","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130394196","display_name":"Han Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1520747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3368","last_page":"3384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9077000021934509,"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":0.9077000021934509,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06199999898672104,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.01850000023841858,"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.6439999938011169},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.6669999957084656},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9760000109672546},{"id":"https://openalex.org/keywords/bloom-s-taxonomy","display_name":"Bloom's taxonomy","score":0.7689999938011169},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.5040000081062317},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"mathematics education","score":0.6299999952316284},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"logical reasoning","score":0.972000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.176","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.176","pdf_url":"https://aclanthology.org/2026.findings-eacl.176.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.176","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.176","pdf_url":"https://aclanthology.org/2026.findings-eacl.176.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":[{"score":0.4023627042770386,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140140937.pdf","grobid_xml":"https://content.openalex.org/works/W7140140937.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7037146327","https://openalex.org/W4392019361","https://openalex.org/W4415091034","https://openalex.org/W7165742452","https://openalex.org/W7162803818","https://openalex.org/W7142440946","https://openalex.org/W4417257961","https://openalex.org/W6948249650","https://openalex.org/W4416037036","https://openalex.org/W7133322207"],"abstract_inverted_index":{"Adapting":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"to":[5,16,30,60,84,91],"specialized":[6],"domains":[7],"requires":[8],"high-quality":[9],"instruction":[10,50],"tuning":[11],"datasets,":[12],"which":[13],"are":[14],"expensive":[15],"create":[17],"through":[18],"human":[19,53],"annotation.Existing":[20],"data":[21,86,113,119],"synthesis":[22],"methods":[23],"focus":[24],"on":[25,110],"generalpurpose":[26],"tasks":[27],"and":[28,34,102],"fail":[29],"capture":[31],"domainspecific":[32,49],"terminology":[33],"reasoning":[35],"patterns.To":[36],"address":[37],"this,":[38],"we":[39],"introduce":[40],"DS":[41],"2":[42],"-INSTRUCT,":[43],"a":[44],"zero-shot":[45],"framework":[46,90],"that":[47,107],"generates":[48,57],"datasets":[51,93],"without":[52],"supervision.Our":[54],"approach":[55],"first":[56],"taskinformed":[58],"keywords":[59,72],"ensure":[61,85],"comprehensive":[62],"domain":[63],"coverage.It":[64],"then":[65],"creates":[66],"diverse":[67],"instructions":[68],"by":[69],"pairing":[70],"these":[71],"with":[73],"different":[74],"cognitive":[75],"levels":[76],"from":[77],"Bloom's":[78],"Taxonomy.Finally,":[79],"it":[80],"uses":[81],"self-consistency":[82],"validation":[83],"quality.We":[87],"apply":[88],"this":[89],"generate":[92],"across":[94],"seven":[95],"challenging":[96],"domains,":[97],"such":[98],"as":[99],"mathematics,":[100],"finance,":[101],"logical":[103],"reasoning.Comprehensive":[104],"evaluation":[105],"demonstrates":[106],"models":[108],"fine-tuned":[109],"our":[111],"generated":[112],"achieve":[114],"substantial":[115],"improvements":[116],"over":[117],"existing":[118],"generation":[120],"methods.":[121],"1":[122]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}