{"id":"https://openalex.org/W7140101752","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.68","title":"Comprehensive Study of Bilingual and Multi-category Instruction Pre-training","display_name":"Comprehensive Study of Bilingual and Multi-category Instruction Pre-training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140101752","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.68"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.68","pdf_url":"https://aclanthology.org/2026.findings-eacl.68.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: EACL 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-eacl.68.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130365436","display_name":"Takashi Kodama","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research and Development in Informatics - ICI Bucharest","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["JP","RO"],"is_corresponding":false,"raw_author_name":"Takashi Kodama","raw_affiliation_strings":["Research and Development Center for LLMs , National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Center for LLMs , National Institute of Informatics","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I4210114681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130337102","display_name":"Yusuke Oda","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research and Development in Informatics - ICI Bucharest","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["JP","RO"],"is_corresponding":false,"raw_author_name":"Yusuke Oda","raw_affiliation_strings":["Research and Development Center for LLMs , National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Center for LLMs , National Institute of Informatics","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I4210114681"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.21001533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1323","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12542","display_name":"Second Language Learning and Teaching","score":0.0471000000834465,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13447","display_name":"Educational and Psychological Assessments","score":0.04659999907016754,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2551000118255615},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.22529999911785126}],"concepts":[{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.5077999830245972},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4043000042438507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3873000144958496},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.24199999868869781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22619999945163727},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.22529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.68","pdf_url":"https://aclanthology.org/2026.findings-eacl.68.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.68","pdf_url":"https://aclanthology.org/2026.findings-eacl.68.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8455808758735657,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140101752.pdf","grobid_xml":"https://content.openalex.org/works/W7140101752.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction":[0],"pre-training":[1,13],"(IPT)":[2],"has":[3],"recently":[4],"emerged":[5],"as":[6,27],"an":[7],"effective":[8],"intermediate":[9],"stage":[10],"between":[11,30],"vanilla":[12],"and":[14,32,36,49,51,56,70,101,119],"post-training":[15,106],"for":[16,85],"large":[17,88],"language":[18],"models":[19,86],"(LLMs).However,":[20],"the":[21,28,103],"optimal":[22],"design":[23],"of":[24,105],"IPT":[25,42,61],"corpora-such":[26],"balance":[29],"raw":[31],"instructionresponse":[33,58],"data,":[34],"languages,":[35],"task":[37],"categoriesremains":[38],"unclear.We":[39],"systematically":[40],"study":[41],"corpus":[43],"composition":[44],"using":[45],"a":[46],"bilingual":[47,71],"(English":[48],"Japanese)":[50],"multi-category":[52],"(coding,":[53],"general,":[54],"math,":[55],"reasoning)":[57],"dataset.Through":[59],"extensive":[60],"experiments":[62],"across":[63,108],"four":[64],"base":[65],"models,":[66],"including":[67],"both":[68],"English-centric":[69],"LLMs,":[72],"we":[73],"find":[74],"that:":[75],"(1)":[76],"more":[77],"instruction-response":[78],"data":[79,93],"generally":[80],"enhances":[81],"model":[82],"performance,":[83],"particularly":[84],"with":[87],"VPT":[89],"budgets;(2)":[90],"Japanese":[91],"instruction":[92],"can":[94],"improve":[95,123],"English":[96],"performance":[97,111],"through":[98],"cross-lingual":[99],"transfer;":[100],"(3)":[102],"effectiveness":[104],"varies":[107],"categories:":[109],"coding":[110],"is":[112],"largely":[113],"determined":[114],"during":[115,124],"IPT,":[116],"while":[117],"math":[118],"reasoning":[120],"continue":[121],"to":[122],"posttraining.":[125]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}