{"id":"https://openalex.org/W7167503558","doi":"https://doi.org/10.1109/access.2026.3709895","title":"Toward Energy-Aware LLM Inference for Text2SQL Workflows Through Context-Driven Model Routing","display_name":"Toward Energy-Aware LLM Inference for Text2SQL Workflows Through Context-Driven Model Routing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167503558","doi":"https://doi.org/10.1109/access.2026.3709895"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3709895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709895","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3709895","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002187602","display_name":"Argyris Kokkinis","orcid":"https://orcid.org/0000-0001-5242-0523"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Argyris Kokkinis","raw_affiliation_strings":["Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0001-5242-0523","affiliations":[{"raw_affiliation_string":"Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140110395","display_name":"Charalampos Lagonidis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Charalampos Lagonidis","raw_affiliation_strings":["Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058063953","display_name":"Thanassis Mavropoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Thanassis Mavropoulos","raw_affiliation_strings":["Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065313479","display_name":"Stefanos Vrochidis","orcid":"https://orcid.org/0000-0002-2505-9178"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stefanos Vrochidis","raw_affiliation_strings":["Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0002-2505-9178","affiliations":[{"raw_affiliation_string":"Center for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210134249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134249"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94056961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"101759","last_page":"101773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.23770000040531158,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.23770000040531158,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.10540000349283218,"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/T14347","display_name":"Big Data and Digital Economy","score":0.06719999760389328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5960999727249146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.541100025177002},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5282999873161316},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4058000147342682},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.29760000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3709895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709895","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:27a45548f9694ca09601d6e498725d5c","is_oa":false,"landing_page_url":"https://doaj.org/article/27a45548f9694ca09601d6e498725d5c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 101759-101773 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3709895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709895","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5751526951789856,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,131,150,206],"rapid":[1],"evolution":[2],"of":[3,12,18,254],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"has":[8],"enabled":[9],"the":[10,16,109,181,197],"introduction":[11],"new":[13],"workflows,":[14],"accelerating":[15],"adoption":[17],"conversational":[19,73],"assistants":[20],"and":[21,66,83,87,94,138,184,196,203,217,251],"broadening":[22],"access":[23],"to":[24,30,48,79,134,163,180,192,246],"tasks":[25,187],"that":[26,158,226],"were":[27],"previously":[28,193],"limited":[29],"domain":[31],"experts.":[32],"Among":[33],"these":[34],"applications,":[35],"Text-to-SQL":[36],"(Text2SQL)":[37],"systems":[38],"have":[39,98],"experienced":[40],"significant":[41,227],"progress,":[42],"allowing":[43],"users":[44],"from":[45],"diverse":[46],"domains":[47,216],"interact":[49],"with":[50],"relational":[51,212],"databases":[52,213],"through":[53],"natural":[54],"language":[55],"interfaces.":[56],"Modern":[57],"LLM-based":[58],"pipelines":[59],"translate":[60],"user":[61],"queries":[62],"into":[63],"SQL":[64,182],"statements":[65],"subsequently":[67],"interpret":[68],"query":[69],"results":[70,224],"in":[71,81,103],"a":[72,121,147,170],"manner.":[74],"However,":[75],"as":[76],"LLMs":[77],"continue":[78],"grow":[80],"size":[82],"capability,":[84],"their":[85,165],"computational":[86],"energy":[88,139,204,228],"requirements":[89],"increase":[90],"significantly.":[91],"Inference":[92],"latency":[93],"GPU":[95],"power":[96],"consumption":[97,140],"become":[99],"critical":[100],"concerns,":[101],"particularly":[102],"large-scale":[104],"or":[105],"resource-constrained":[106],"deployments,":[107],"highlighting":[108],"need":[110],"for":[111,127],"more":[112,249],"sustainable":[113,252],"inference":[114],"strategies.":[115],"In":[116],"this":[117],"work,":[118],"we":[119],"propose":[120],"dynamic,":[122],"energy-aware":[123],"LLM":[124,161],"selection":[125],"methodology":[126,207],"end-to-end":[128],"Text2SQL":[129,221],"workflows.":[130],"objective":[132],"is":[133,208],"balance":[135],"response":[136,239],"quality":[137,240],"by":[141,169],"selecting":[142],"appropriate":[143],"model":[144],"configurations":[145],"on":[146,189,210],"per-query":[148],"basis.":[149],"proposed":[151],"framework":[152],"includes":[153],"an":[154],"offline":[155],"profiling":[156],"phase":[157],"evaluates":[159],"multiple":[160],"combinations":[162],"characterize":[164],"quality–energy":[166],"trade-offs,":[167],"followed":[168],"runtime":[171],"routing":[172],"mechanism.":[173],"A":[174],"KNN-based":[175],"router":[176],"assigns":[177],"suitable":[178],"models":[179],"generation":[183],"result":[185],"interpretation":[186],"based":[188],"contextual":[190],"similarity":[191],"profiled":[194],"questions":[195],"desired":[198],"operating":[199],"point":[200],"between":[201],"performance":[202],"efficiency.":[205],"evaluated":[209],"five":[211],"across":[214],"different":[215],"compared":[218,245],"against":[219],"state-of-the-art":[220],"frameworks.":[222],"Experimental":[223],"demonstrate":[225],"savings":[229],"(29%":[230],"-":[231],"52%)":[232],"can":[233],"be":[234],"achieved":[235],"while":[236],"maintaining":[237],"competitive":[238],"(less":[241],"than":[242],"3%":[243],"degradation)":[244],"state-of-the-art,":[247],"supporting":[248],"efficient":[250],"deployment":[253],"LLM-powered":[255],"database":[256],"systems.":[257]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2026-07-07T00:00:00"}