{"id":"https://openalex.org/W4406355124","doi":"https://doi.org/10.1109/ictc62082.2024.10826936","title":"Automated Knowledge Distillation Pipeline for Domain-Specific Small-Scale Language Models","display_name":"Automated Knowledge Distillation Pipeline for Domain-Specific Small-Scale Language Models","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4406355124","doi":"https://doi.org/10.1109/ictc62082.2024.10826936"},"language":"en","primary_location":{"id":"doi:10.1109/ictc62082.2024.10826936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc62082.2024.10826936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010710953","display_name":"Minyoung Kyoung","orcid":"https://orcid.org/0009-0006-2814-9386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minyoung Kyoung","raw_affiliation_strings":["AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyungbae Jeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyungbae Jeon","raw_affiliation_strings":["AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101467986","display_name":"Sungeun Park","orcid":"https://orcid.org/0000-0002-7383-1409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungeun Park","raw_affiliation_strings":["AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Tutorus Labs Inc.,Daejeon,Republic of Korea","institution_ids":[]}]}],"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":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.7189000248908997,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7189000248908997,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.6682999730110168,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.6146000027656555,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/pipeline","display_name":"Pipeline (software)","score":0.7516320943832397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.720779538154602},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6483854651451111},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6345019340515137},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5766951441764832},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.46347105503082275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42261797189712524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3539298176765442},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.23794907331466675},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1945936679840088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05893987417221069}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7516320943832397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720779538154602},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6483854651451111},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6345019340515137},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5766951441764832},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.46347105503082275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42261797189712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3539298176765442},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.23794907331466675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1945936679840088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05893987417221069},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1109/ictc62082.2024.10826936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc62082.2024.10826936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7860940854","display_name":null,"funder_award_id":"RS-2024-00340342","funder_id":"https://openalex.org/F4320322006","funder_display_name":"Ministry of Culture, Sports and Tourism"}],"funders":[{"id":"https://openalex.org/F4320322006","display_name":"Ministry of Culture, Sports and Tourism","ror":"https://ror.org/02fkk6k65"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2798405286","https://openalex.org/W2979826702","https://openalex.org/W4389519254","https://openalex.org/W6796581206"],"related_works":["https://openalex.org/W2057033141","https://openalex.org/W4252103056","https://openalex.org/W2917823318","https://openalex.org/W2917572814","https://openalex.org/W4242858628","https://openalex.org/W2979406678","https://openalex.org/W2915857720","https://openalex.org/W2916715723","https://openalex.org/W3006129753","https://openalex.org/W2085476653"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,27,38],"demonstrated":[5],"notable":[6],"advancements":[7],"across":[8],"a":[9],"range":[10],"of":[11,20,41,79],"natural":[12],"language":[13],"processing":[14],"tasks.":[15],"However,":[16],"the":[17,29,39,76,94],"high":[18],"costs":[19],"training":[21,43],"and":[22,45],"deploying":[23],"these":[24,60],"large":[25],"models":[26],"intensified":[28],"interest":[30],"in":[31],"developing":[32],"smaller-scale":[33],"LLMs":[34],"(sLLMs).":[35],"Although":[36],"sLLMs":[37,73],"advantage":[40],"reduced":[42],"resources":[44],"serving":[46],"costs,":[47],"they":[48],"typically":[49],"exhibit":[50],"lower":[51],"performance":[52,91],"due":[53],"to":[54,69,93],"their":[55],"limited":[56],"capacity.":[57],"To":[58],"overcome":[59],"limitations,":[61],"we":[62],"propose":[63],"an":[64],"automated":[65],"knowledge":[66],"distillation":[67],"pipeline":[68],"develop":[70],"domain-specific":[71],"specialized":[72],"by":[74],"leveraging":[75],"extensive":[77],"capabilities":[78],"larger":[80],"models.":[81],"Our":[82],"experimental":[83],"results":[84],"demonstrate":[85],"that":[86],"our":[87],"approach":[88],"significantly":[89],"improves":[90],"compared":[92],"original":[95],"sLLMs.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}