{"id":"https://openalex.org/W4412945321","doi":"https://doi.org/10.18653/v1/2025.acl-long.625","title":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","display_name":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945321","doi":"https://doi.org/10.18653/v1/2025.acl-long.625"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.625","pdf_url":"https://aclanthology.org/2025.acl-long.625.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 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.625.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115076694","display_name":"Zhuang Li","orcid":"https://orcid.org/0009-0006-3870-4275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056256808","display_name":"Yuncheng Hua","orcid":"https://orcid.org/0000-0002-4238-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuncheng Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062855474","display_name":"Thuy-Trang Vu","orcid":"https://orcid.org/0009-0005-6296-4184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thuy-Trang Vu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043429023","display_name":"Haolan Zhan","orcid":"https://orcid.org/0000-0001-9628-5992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haolan Zhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008486397","display_name":"Lizhen Qu","orcid":"https://orcid.org/0000-0002-7764-431X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lizhen Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gholamreza Haffari","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12756","last_page":"12790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9855999946594238,"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":0.9855999946594238,"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/T10028","display_name":"Topic Modeling","score":0.9848999977111816,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9401999711990356,"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":0.7933874130249023},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.760230541229248},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7429283857345581},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7240427136421204},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6094179153442383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053163170814514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4674552083015442},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4594792425632477},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39864808320999146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34189552068710327},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32053065299987793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933874130249023},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.760230541229248},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7429283857345581},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7240427136421204},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6094179153442383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053163170814514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4674552083015442},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4594792425632477},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39864808320999146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34189552068710327},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32053065299987793},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.625","pdf_url":"https://aclanthology.org/2025.acl-long.625.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 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.625","pdf_url":"https://aclanthology.org/2025.acl-long.625.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 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945321.pdf","grobid_xml":"https://content.openalex.org/works/W4412945321.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2188500270","https://openalex.org/W2349768204","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2793336762","https://openalex.org/W2387017288","https://openalex.org/W1494981348","https://openalex.org/W1546381263"],"abstract_inverted_index":{"Zhuang":[0],"Li,":[1],"Yuncheng":[2],"Hua,":[3],"Thuy-Trang":[4],"Vu,":[5],"Haolan":[6],"Zhan,":[7],"Lizhen":[8],"Qu,":[9],"Gholamreza":[10],"Haffari.":[11],"Proceedings":[12],"of":[13,18],"the":[14,19],"63rd":[15],"Annual":[16],"Meeting":[17],"Association":[20],"for":[21],"Computational":[22],"Linguistics":[23],"(Volume":[24],"1:":[25],"Long":[26],"Papers).":[27],"2025.":[28]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
