@inproceedings{dutta-etal-2026-benchmarking,
    title = "Benchmarking the Energy Savings with Speculative Decoding Strategies",
    author = "Dutta, Rohit  and
      Koley, Paramita  and
      Poddar, Soham  and
      Misra, Janardan  and
      Podder, Sanjay  and
      Balani, Naveen  and
      Ghosh, Saptarshi  and
      Ganguly, Niloy",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.249/",
    pages = "4737--4748",
    ISBN = "979-8-89176-386-9",
    abstract = "Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors {--} model size and family, speculative decoding strategies, and dataset characteristics {--} influence the energy optimizations."
}