{"id":"https://openalex.org/W4407682194","doi":"https://doi.org/10.1145/3718096","title":"Efficiency and Performance Optimization in Large Language Models through IB Fine-Tuning","display_name":"Efficiency and Performance Optimization in Large Language Models through IB Fine-Tuning","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4407682194","doi":"https://doi.org/10.1145/3718096"},"language":"en","primary_location":{"id":"doi:10.1145/3718096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3718096","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5077222686","display_name":"Ashly Ann Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashly Ann Jo","raw_affiliation_strings":["FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India"],"raw_orcid":"https://orcid.org/0009-0009-8641-5226","affiliations":[{"raw_affiliation_string":"FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064255183","display_name":"Ebin Deni Raj","orcid":"https://orcid.org/0000-0003-3339-8601"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ebin Deni Raj","raw_affiliation_strings":["FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India"],"raw_orcid":"https://orcid.org/0000-0003-3339-8601","affiliations":[{"raw_affiliation_string":"FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083804893","display_name":"Jayakrushna Sahoo","orcid":"https://orcid.org/0000-0002-4514-3916"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayakrushna Sahoo","raw_affiliation_strings":["FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India"],"raw_orcid":"https://orcid.org/0000-0002-4514-3916","affiliations":[{"raw_affiliation_string":"FACTS-H Lab, Indian Institute of Information Technology, Kottayam, India","institution_ids":["https://openalex.org/I26072440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94623039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9818999767303467,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9801999926567078,"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":0.898461103439331},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5017521381378174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3751404881477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.898461103439331},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5017521381378174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3751404881477356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3718096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3718096","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2683470288","https://openalex.org/W2750779823","https://openalex.org/W2798381792","https://openalex.org/W2880214242","https://openalex.org/W2989653627","https://openalex.org/W2995653869","https://openalex.org/W3013104126","https://openalex.org/W3019623663","https://openalex.org/W3034347188","https://openalex.org/W3043058418","https://openalex.org/W3045310944","https://openalex.org/W3092019241","https://openalex.org/W3099793224","https://openalex.org/W3119169886","https://openalex.org/W3122230257","https://openalex.org/W3160638507","https://openalex.org/W3165830952","https://openalex.org/W3168867926","https://openalex.org/W3198659451","https://openalex.org/W3198675127","https://openalex.org/W3205177049","https://openalex.org/W3205235328","https://openalex.org/W3211702313","https://openalex.org/W3212472206","https://openalex.org/W3212653573","https://openalex.org/W4212926655","https://openalex.org/W4221149036","https://openalex.org/W4225139287","https://openalex.org/W4225793993","https://openalex.org/W4226020328","https://openalex.org/W4226278401","https://openalex.org/W4286850742","https://openalex.org/W4286987939","https://openalex.org/W4287025617","https://openalex.org/W4293469690","https://openalex.org/W4297749952","https://openalex.org/W4312359569","https://openalex.org/W4322614701","https://openalex.org/W4322766882","https://openalex.org/W4324373918","https://openalex.org/W4362656079","https://openalex.org/W4367061121","https://openalex.org/W4379876611","https://openalex.org/W4380992741","https://openalex.org/W4381785866","https://openalex.org/W4382240676","https://openalex.org/W4382246105","https://openalex.org/W4385287322","https://openalex.org/W4385456320","https://openalex.org/W4385571039","https://openalex.org/W4385878021","https://openalex.org/W4386978016","https://openalex.org/W4387436590","https://openalex.org/W4388183174","https://openalex.org/W4388277090","https://openalex.org/W4390490761","https://openalex.org/W4391136507","https://openalex.org/W4391855109","https://openalex.org/W4392376454","https://openalex.org/W4394877201","https://openalex.org/W4394906863","https://openalex.org/W4399547912","https://openalex.org/W4400118952","https://openalex.org/W4400484590","https://openalex.org/W4404031275","https://openalex.org/W6801962987","https://openalex.org/W6803107227","https://openalex.org/W6869100048"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,73,80,94,172],"rapidly":[2],"evolving":[3],"field":[4],"of":[5],"Natural":[6],"Language":[7,15],"Processing":[8],"(NLP),":[9],"optimizing":[10],"methods":[11,50],"for":[12,21,64],"fine-tuning":[13,49,65,148],"Large":[14],"Models":[16],"(LLMs)":[17],"is":[18,28,67],"increasingly":[19],"critical":[20,75],"improving":[22],"generalization":[23],"and":[24,35,52,76,91,101,110,131,134,167,185,189],"performance.":[25,142],"Fine-tuning":[26],"LLMs":[27,45,66],"challenging":[29],"due":[30],"to":[31,38,98,113,158],"high":[32,140],"costs,":[33,181],"overfitting,":[34],"difficulty":[36],"adapting":[37],"diverse":[39,150],"tasks.":[40],"These":[41],"challenges":[42],"grow":[43],"as":[44],"scale,":[46],"making":[47],"traditional":[48],"inefficient":[51],"expensive.":[53],"To":[54],"address":[55],"these":[56],"issues,":[57],"a":[58,86,154],"novel":[59],"Information":[60],"Bottleneck":[61],"(IB)":[62],"method":[63,96,174],"proposed,":[68],"focusing":[69],"on":[70],"retaining":[71],"only":[72],"most":[74],"relevant":[77],"information":[78,89],"in":[79],"model\u2019s":[81],"internal":[82],"representations.":[83],"By":[84],"striking":[85],"balance":[87],"between":[88],"compression":[90,126],"predictive":[92,136],"relevance,":[93,137],"IB":[95,173],"aims":[97],"reduce":[99],"overfitting":[100],"enhance":[102,114,159],"generalization.":[103],"This":[104],"approach":[105],"also":[106],"integrates":[107],"reinforcement":[108],"learning":[109,112],"continual":[111],"LLM":[115,187],"performance":[116],"further.":[117],"The":[118,143,162],"proposed":[119,144,163],"framework":[120,164],"considers":[121],"two":[122],"key":[123],"metrics:":[124],"(1)":[125],"effectiveness,":[127],"which":[128,138],"reduces":[129],"redundancy":[130],"improves":[132,175],"generalization,":[133],"(2)":[135],"ensures":[139],"task-specific":[141],"scheme":[145],"achieves":[146],"scalable":[147],"across":[149],"NLP":[151],"tasks":[152],"using":[153],"lightweight":[155],"proxy":[156],"model":[157],"computational":[160,180],"efficiency.":[161],"empirical":[165],"evaluations":[166],"ablation":[168],"studies":[169],"show":[170],"that":[171],"accuracy":[176],"while":[177],"significantly":[178],"reducing":[179],"enabling":[182],"efficient,":[183],"interpretable,":[184],"adaptable":[186],"optimization":[188],"increasing":[190],"convergence.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}