{"id":"https://openalex.org/W7140100181","doi":"https://doi.org/10.18653/v1/2026.eacl-long.255","title":"An Empirical Study of Speculative Decoding for Small Language Models","display_name":"An Empirical Study of Speculative Decoding for Small Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140100181","doi":"https://doi.org/10.18653/v1/2026.eacl-long.255"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.255","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.255","pdf_url":"https://aclanthology.org/2026.eacl-long.255.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.255.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130401168","display_name":"Luca Mainardi","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Luca Mainardi","raw_affiliation_strings":["Eindhoven University of Technology Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130344581","display_name":"Selcuk Sandikci","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Selcuk Sandikci","raw_affiliation_strings":["Eindhoven University of Technology Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016794035","display_name":"Joaquin Vanschoren","orcid":"https://orcid.org/0000-0001-7044-9805"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joaquin Vanschoren","raw_affiliation_strings":["Eindhoven University of Technology Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5483","last_page":"5497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.14380000531673431,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.14380000531673431,"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/T10028","display_name":"Topic Modeling","score":0.10220000147819519,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.08910000324249268,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.6098999977111816},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5029000043869019},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3327000141143799},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31119999289512634},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.30059999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865000128746033},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4577000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.255","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.255","pdf_url":"https://aclanthology.org/2026.eacl-long.255.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.255","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.255","pdf_url":"https://aclanthology.org/2026.eacl-long.255.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5601522922515869,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7699649992","display_name":"European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams","funder_award_id":"101214398","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140100181.pdf","grobid_xml":"https://content.openalex.org/works/W7140100181.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speculative":[0],"decoding":[1,54],"has":[2,16],"emerged":[3],"as":[4],"a":[5,24],"promising":[6],"approach":[7],"to":[8,97],"accelerate":[9],"Large":[10],"Language":[11],"Model":[12],"inference.However,":[13],"existing":[14],"research":[15],"predominantly":[17],"focused":[18],"on":[19,127],"7B-70B":[20],"parameters":[21],"models,":[22],"leaving":[23],"critical":[25],"knowledge":[26],"gap":[27],"for":[28,38,56,134],"small":[29,57,87,136],"language":[30,58],"models":[31],"(1-2B":[32],"parameters)":[33],"that":[34,72,90],"are":[35],"increasingly":[36],"important":[37],"edge":[39],"computing":[40],"and":[41,70],"agentic":[42],"AI":[43],"systems.This":[44],"paper":[45],"presents":[46],"the":[47,80,98],"first":[48],"comprehensive":[49],"empirical":[50],"study":[51],"of":[52,86,101],"speculative":[53],"techniques":[55],"models.We":[59,88],"evaluate":[60],"five":[61],"distinct":[62],"method":[63],"categories":[64],"across":[65],"three":[66],"representative":[67],"model":[68,137],"families":[69],"reveal":[71],"drafting":[73,93],"overhead,":[74],"rather":[75],"than":[76],"draft":[77,115],"quality,":[78],"becomes":[79],"primary":[81],"bottleneck":[82],"fundamentally":[83],"limiting":[84],"acceleration":[85,109],"demonstrate":[89],"traditional":[91],"independent":[92],"fails":[94],"completely":[95],"due":[96],"suboptimal":[99],"architecture":[100],"available":[102],"drafters,":[103],"while":[104],"self-drafting":[105],"methods":[106,119],"achieve":[107],"meaningful":[108],"only":[110],"when":[111],"employing":[112],"sufficiently":[113],"efficient":[114],"modules.In":[116],"contrast,":[117],"retrieval-based":[118],"with":[120],"negligible":[121],"computational":[122],"overhead":[123],"yield":[124],"consistent":[125],"gains.Based":[126],"these":[128],"insights,":[129],"we":[130],"establish":[131],"practical":[132],"guidelines":[133],"effective":[135],"acceleration.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}