{"id":"https://openalex.org/W4412082096","doi":"https://doi.org/10.1109/cai64502.2025.00067","title":"Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights","display_name":"Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4412082096","doi":"https://doi.org/10.1109/cai64502.2025.00067"},"language":"en","primary_location":{"id":"doi:10.1109/cai64502.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cai64502.2025.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Artificial Intelligence (CAI)","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":null,"display_name":"Tahniat Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tahniat Khan","raw_affiliation_strings":["Vector Institute,Industry Innovation,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vector Institute,Industry Innovation,Toronto,Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114382677","display_name":"Soroor Motie","orcid":"https://orcid.org/0000-0002-3675-4774"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Soroor Motie","raw_affiliation_strings":["Vector Institute, University of Ottawa,Ottawa,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vector Institute, University of Ottawa,Ottawa,Canada","institution_ids":["https://openalex.org/I153718931","https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026969522","display_name":"Sedef Akinli Ko\u00e7ak","orcid":"https://orcid.org/0009-0009-6271-415X"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sedef Akinli Kocak","raw_affiliation_strings":["Vector Institute,Industry Innovation,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vector Institute,Industry Innovation,Toronto,Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053939840","display_name":"Shaina Raza","orcid":"https://orcid.org/0000-0003-1061-5845"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shaina Raza","raw_affiliation_strings":["AI Engineering, Vector Institute,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Engineering, Vector Institute,Toronto,Canada","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7111,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98675346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7644000053405762,"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":0.7644000053405762,"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":0.738311767578125},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.48636797070503235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3354794979095459},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09697961807250977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738311767578125},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.48636797070503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3354794979095459},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09697961807250977},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cai64502.2025.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cai64502.2025.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Artificial Intelligence (CAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1546425147","https://openalex.org/W2950372567","https://openalex.org/W3182375976","https://openalex.org/W4379743664","https://openalex.org/W4391407061","https://openalex.org/W4392593558","https://openalex.org/W4399397061","https://openalex.org/W4399913870","https://openalex.org/W4400414492","https://openalex.org/W4402670692","https://openalex.org/W4402727764","https://openalex.org/W4404057367","https://openalex.org/W4404391248","https://openalex.org/W4405640497"],"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":{"The":[0,100],"rapid":[1],"adoption":[2],"of":[3,24,33,40,69,114],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"has":[8],"led":[9],"to":[10,21,42],"significant":[11],"energy":[12,84],"consumption":[13,85],"and":[14,52,59,86,116],"carbon":[15,67,87],"emissions,":[16],"posing":[17],"a":[18,49],"critical":[19],"challenge":[20],"the":[22,31,38,66],"sustainability":[23,107],"generative":[25],"AI":[26,109],"technologies.":[27],"This":[28],"paper":[29],"explores":[30],"integration":[32],"energy-efficient":[34],"optimization":[35],"techniques":[36,62],"in":[37,108],"deployment":[39],"LLMs":[41,70],"address":[43],"these":[44,80],"environmental":[45],"concerns.":[46],"We":[47],"present":[48],"case":[50],"study":[51],"framework":[53],"that":[54,79],"demonstrate":[55],"how":[56],"strategic":[57],"quantization":[58],"local":[60],"inference":[61],"can":[63,82],"substantially":[64],"lower":[65],"footprints":[68],"without":[71],"compromising":[72],"their":[73],"operational":[74],"effectiveness.":[75],"Experimental":[76],"results":[77],"reveal":[78],"methods":[81],"reduce":[83],"emissions":[88],"by":[89],"up":[90],"to$45{\\%}$post":[91],"quantization,":[92],"making":[93],"them":[94],"particularly":[95],"suitable":[96],"for":[97,105],"resource-constrained":[98],"environments.":[99],"findings":[101],"provide":[102],"actionable":[103],"insights":[104],"achieving":[106],"while":[110],"maintaining":[111],"high":[112],"levels":[113],"accuracy":[115],"responsiveness.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}