{"id":"https://openalex.org/W4412887018","doi":"https://doi.org/10.18653/v1/2025.acl-industry.32","title":"Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code","display_name":"Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887018","doi":"https://doi.org/10.18653/v1/2025.acl-industry.32"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-industry.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-industry.32","pdf_url":"https://aclanthology.org/2025.acl-industry.32.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-industry.32.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102375302","display_name":"Geonmo Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geonmo Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jaeho Kwak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaeho Kwak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haksoo Moon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haksoo Moon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055470439","display_name":"Hyungbo Shim","orcid":"https://orcid.org/0000-0002-5972-8114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun Seung Shim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004150277","display_name":"Yu Jin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Jin Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061301511","display_name":"Byoungjip Kim","orcid":"https://orcid.org/0000-0002-1227-977X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byoungjip Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066049461","display_name":"Moontae Lee","orcid":"https://orcid.org/0000-0001-5542-3463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moontae Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hyejeong Jeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyejeong Jeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.08557664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9412000179290771,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9412000179290771,"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/computer-science","display_name":"Computer science","score":0.7049174904823303},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.614383339881897},{"id":"https://openalex.org/keywords/stride","display_name":"STRIDE","score":0.612346351146698},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.6095665693283081},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.580056369304657},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5800156593322754},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2803082764148712},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17024177312850952},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14745432138442993},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.09649065136909485},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08486437797546387},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07042577862739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049174904823303},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.614383339881897},{"id":"https://openalex.org/C18007350","wikidata":"https://www.wikidata.org/wiki/Q7394815","display_name":"STRIDE","level":2,"score":0.612346351146698},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.6095665693283081},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.580056369304657},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5800156593322754},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2803082764148712},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17024177312850952},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14745432138442993},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.09649065136909485},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08486437797546387},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07042577862739563},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-industry.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-industry.32","pdf_url":"https://aclanthology.org/2025.acl-industry.32.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-industry.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-industry.32","pdf_url":"https://aclanthology.org/2025.acl-industry.32.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887018.pdf","grobid_xml":"https://content.openalex.org/works/W4412887018.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2347597433","https://openalex.org/W2389023277","https://openalex.org/W2562411628","https://openalex.org/W3034772098","https://openalex.org/W2100563491","https://openalex.org/W2124672917","https://openalex.org/W4289821489","https://openalex.org/W4297820790","https://openalex.org/W2333025614","https://openalex.org/W2388211622"],"abstract_inverted_index":{"Geonmo":[0],"Gu,":[1],"Jaeho":[2],"Kwak,":[3],"Haksoo":[4],"Moon,":[5],"Hyun":[6],"Seung":[7],"Shim,":[8],"Yu":[9],"Jin":[10],"Kim,":[11,13],"Byoungjip":[12],"Moontae":[14],"Lee,":[15],"Hyejeong":[16],"Jeon.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"63rd":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"6:":[31],"Industry":[32],"Track).":[33],"2025.":[34]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
