{"id":"https://openalex.org/W7118159666","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315280","title":"CAKD: A Confidence-Aware Knowledge Distillation Approach for Building Compact and Efficient LLMs","display_name":"CAKD: A Confidence-Aware Knowledge Distillation Approach for Building Compact and Efficient LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118159666","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315280"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},"type":"article","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/A5121967708","display_name":"Mohammad Basheer Kotit","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Mohammad Basheer Kotit","raw_affiliation_strings":["Qatar University,Doha,Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024523877","display_name":"Omama Hamad","orcid":"https://orcid.org/0000-0002-5184-2668"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Omama Hamad","raw_affiliation_strings":["Qatar University,Doha,Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121648537","display_name":"Khaled Shaban","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Khaled Shaban","raw_affiliation_strings":["Qatar University,Doha,Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030894498","display_name":"Ali Hamdi","orcid":"https://orcid.org/0000-0002-2301-6588"},"institutions":[{"id":"https://openalex.org/I895027328","display_name":"October University of Modern Sciences and Arts","ror":"https://ror.org/01nvnhx40","country_code":"EG","type":"education","lineage":["https://openalex.org/I895027328"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Hamdi","raw_affiliation_strings":["MSA University,Cairo,Egypt"],"affiliations":[{"raw_affiliation_string":"MSA University,Cairo,Egypt","institution_ids":["https://openalex.org/I895027328"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121967708"],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85916761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2815999984741211,"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":0.2815999984741211,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18569999933242798,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.05209999904036522,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8791000247001648},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6546000242233276},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6481999754905701},{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.4165000021457672},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.337799996137619},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.33219999074935913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32659998536109924}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8791000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955000162124634},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782999992370605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5357000231742859},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2407386500","https://openalex.org/W2963825865","https://openalex.org/W2963929190","https://openalex.org/W2970419734","https://openalex.org/W2997006708","https://openalex.org/W3034368386","https://openalex.org/W3034457371","https://openalex.org/W3035050380","https://openalex.org/W3101248447","https://openalex.org/W3105966348","https://openalex.org/W3106302287","https://openalex.org/W3159704894","https://openalex.org/W3169483174","https://openalex.org/W3200808010","https://openalex.org/W4225934689","https://openalex.org/W4285157242","https://openalex.org/W4287854750","https://openalex.org/W4385245566","https://openalex.org/W4389519858","https://openalex.org/W4389523711","https://openalex.org/W4389524481","https://openalex.org/W4402667003","https://openalex.org/W4402671533"],"related_works":[],"abstract_inverted_index":{"High-quality":[0],"models":[1,35,59,82],"across":[2],"various":[3],"natural":[4],"language":[5],"processing":[6],"tasks,":[7],"such":[8],"as":[9],"summarization":[10,119],"and":[11,22,52,113,128,137,156],"chatbots,":[12],"often":[13],"rely":[14],"on":[15,117,124,134],"large":[16],"architectures,":[17],"making":[18],"them":[19],"computationally":[20],"intensive":[21],"challenging":[23],"to":[24,36],"deploy":[25],"in":[26,110],"resource-constrained":[27],"environments.":[28],"While":[29],"knowledge":[30],"distillation":[31,102],"enables":[32],"smaller":[33],"student":[34,81],"approximate":[37],"the":[38,63,78,86,101,125,135],"performance":[39,112,145],"of":[40,80,153],"larger":[41,148],"teacher":[42,58,87,149],"models,":[43,150],"existing":[44],"methods":[45],"frequently":[46],"encounter":[47],"significant":[48,144],"trade-offs":[49],"between":[50],"accuracy":[51],"efficiency.":[53,114],"Additionally,":[54],"uncertain":[55],"predictions":[56,91],"from":[57],"can":[60],"negatively":[61],"impact":[62],"student\u2019s":[64],"learning":[65],"process.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"introduce":[71],"CAKD,":[72],"a":[73,121],"novel":[74],"approach":[75],"that":[76,141],"optimizes":[77],"training":[79],"by":[83],"selectively":[84],"emphasizing":[85],"model\u2019s":[88],"most":[89],"reliable":[90],"using":[92],"confidence":[93,98],"scores.":[94],"By":[95],"integrating":[96],"entropybased":[97],"weighting":[99],"into":[100],"loss,":[103],"CAKD":[104,142],"effectively":[105],"prioritizes":[106],"high-confidence":[107],"samples,":[108],"resulting":[109],"improved":[111],"Our":[115],"experiments":[116],"text":[118],"(using":[120,131],"BART-based":[122],"model":[123,133],"CNN/DM":[126],"dataset)":[127],"chatbot":[129],"tasks":[130],"Llamabased":[132],"DailyDialog":[136],"PersonaChat":[138],"datasets)":[139],"demonstrate":[140],"achieves":[143],"gains":[146],"over":[147],"with":[151],"improvements":[152],"10.53,":[154],"2.1":[155],"0.38":[157],"ROUGE-L":[158],"points":[159],"respectively.":[160]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-05T00:00:00"}