{"id":"https://openalex.org/W4400680910","doi":"https://doi.org/10.1109/ieeeconf61558.2024.10585529","title":"Fine-tuning the Gemma model for Kaggle Assistant","display_name":"Fine-tuning the Gemma model for Kaggle Assistant","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4400680910","doi":"https://doi.org/10.1109/ieeeconf61558.2024.10585529"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf61558.2024.10585529","doi":"https://doi.org/10.1109/ieeeconf61558.2024.10585529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf61558.2024.10585529","pdf_url":null,"source":{"id":"https://openalex.org/S7407114025","display_name":"IEEE AITU: Digital Generation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE AITU: Digital Generation","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5104601679","display_name":"Arman Zhalgasbayev","orcid":"https://orcid.org/0000-0001-8507-6845","observed_orcids":["https://orcid.org/0000-0001-8507-6845"]},"institutions":[{"id":"https://openalex.org/I4405257690","display_name":"Astana IT University","ror":"https://ror.org/05jnvbc31","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4405257690"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Arman Zhalgasbayev","raw_affiliation_strings":["Sofrware Engineering Student, Astana IT University,Astana,Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-8507-6845","affiliations":[{"raw_affiliation_string":"Sofrware Engineering Student, Astana IT University,Astana,Kazakhstan","institution_ids":["https://openalex.org/I4405257690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104617952","display_name":"Ali Khauazkhan","orcid":"https://orcid.org/0009-0007-2411-2145","observed_orcids":["https://orcid.org/0009-0007-2411-2145"]},"institutions":[{"id":"https://openalex.org/I4405257690","display_name":"Astana IT University","ror":"https://ror.org/05jnvbc31","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4405257690"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Ali Khauazkhan","raw_affiliation_strings":["Big Data Analysis Student, Astana IT University,Astana,Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0007-2411-2145","affiliations":[{"raw_affiliation_string":"Big Data Analysis Student, Astana IT University,Astana,Kazakhstan","institution_ids":["https://openalex.org/I4405257690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060821491","display_name":"Zhibek N. Sarsenova","orcid":"https://orcid.org/0000-0002-7780-8070","observed_orcids":["https://orcid.org/0000-0002-7780-8070"]},"institutions":[{"id":"https://openalex.org/I4405257690","display_name":"Astana IT University","ror":"https://ror.org/05jnvbc31","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4405257690"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhibek Sarsenova","raw_affiliation_strings":["Astana IT University,Computer Engineering department,Astana,Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-7780-8070","affiliations":[{"raw_affiliation_string":"Astana IT University,Computer Engineering department,Astana,Kazakhstan","institution_ids":["https://openalex.org/I4405257690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405257690"],"apc_list":null,"apc_paid":null,"fwci":0.6108,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68601491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8901000022888184,"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":0.8901000022888184,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05820000171661377,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.006800000090152025,"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/gemma","display_name":"Gemma","score":0.7459999918937683},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7269999980926514},{"id":"https://openalex.org/keywords/open-source-llms","display_name":"open-source LLMs","score":0.6520000100135803},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.5640000104904175},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C170806853","wikidata":"https://www.wikidata.org/wiki/Q2746099","display_name":"Gemma","level":2,"score":0.8356010913848877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6357919573783875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08541584014892578},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf61558.2024.10585529","doi":"https://doi.org/10.1109/ieeeconf61558.2024.10585529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf61558.2024.10585529","pdf_url":null,"source":{"id":"https://openalex.org/S7407114025","display_name":"IEEE AITU: Digital Generation","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE AITU: Digital Generation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3016867997","https://openalex.org/W3168867926","https://openalex.org/W3195140297","https://openalex.org/W3213321795","https://openalex.org/W4206114143","https://openalex.org/W4249753682","https://openalex.org/W6796581206"],"related_works":["https://openalex.org/W7143630455","https://openalex.org/W7117138615","https://openalex.org/W7159897212","https://openalex.org/W7166524735","https://openalex.org/W4401840063","https://openalex.org/W7128609400","https://openalex.org/W7128284571","https://openalex.org/W4391591639","https://openalex.org/W7134918150","https://openalex.org/W4392822465"],"abstract_inverted_index":{"The":[0,43,89,130],"emergence":[1],"of":[2,18,28,46,58,91,100,107,132,170],"advanced":[3],"open-source":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"opens":[9],"new":[10],"opportunities":[11],"for":[12,61,163],"researchers":[13],"and":[14,87,102,113,143,155,168],"accelerates":[15],"the":[16,26,38,47,52,70,77,92,122,136,152,171],"development":[17],"generative":[19],"AI.":[20],"This":[21],"study":[22,48,75],"focuses":[23],"on":[24],"harnessing":[25],"potential":[27,117],"Gemma,":[29],"Google's":[30],"recently":[31],"released":[32],"open":[33],"source":[34],"LLM,":[35],"to":[36,50,84,139,145,183],"develop":[37],"Kaggle":[39,148,190],"assistant":[40,66],"through":[41,175],"fine-tuning.":[42],"main":[44],"objective":[45],"was":[49],"investigate":[51],"Low-Rank":[53],"Adaptation":[54],"(LoRA)":[55],"fine-tuning":[56,90,134],"method":[57,83],"Gemma":[59,71,172],"model":[60,93,123],"building":[62],"a":[63,95,103,160],"robust":[64],"AI":[65],"in":[67,127,188,192],"Kaggle.":[68],"Using":[69],"2B":[72],"variant,":[73],"this":[74,128],"applies":[76],"Latent":[78],"Consistency":[79],"Model":[80],"-":[81],"LoRA":[82,133,179],"improve":[85],"interpretability":[86],"performance.":[88],"achieved":[94],"sparse":[96,104],"categorical":[97,105],"cross-entropy":[98],"(Loss)":[99],"0.4943":[101],"precision":[106],"0.7753.":[108],"Although":[109],"experiments":[110],"with":[111],"epochs":[112],"batch":[114],"sizes":[115],"revealed":[116],"overbuilding":[118],"after":[119],"10":[120],"epochs,":[121],"shows":[124],"acceptable":[125],"performance":[126],"range.":[129],"integration":[131],"enhances":[135],"model's":[137],"ability":[138],"provide":[140],"accurate":[141],"recommendations":[142],"conclusions":[144],"users":[146,191],"solving":[147],"problems,":[149],"thereby":[150],"improving":[151],"user":[153],"experience":[154],"reinforcing":[156],"its":[157,185],"utility":[158],"as":[159,178],"valuable":[161],"resource":[162],"data":[164,194],"scientists.":[165],"Further":[166],"refinement":[167],"adaptation":[169],"model,":[173],"especially":[174],"techniques":[176],"such":[177],"fine-tuning,":[180],"are":[181],"critical":[182],"ensure":[184],"continued":[186],"effectiveness":[187],"assisting":[189],"their":[193],"science":[195],"endeavors.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2024-07-17T00:00:00"}