@inproceedings{li-etal-2025-speculative,
    title = "Speculative Decoding for Multi-Sample Inference",
    author = "Li, Yiwei  and
      Shi, Jiayi  and
      Feng, Shaoxiong  and
      Yuan, Peiwen  and
      Wang, Xinglin  and
      Zhang, Yueqi  and
      Zhang, Ji  and
      Tan, Chuyi  and
      Pan, Boyuan  and
      Hu, Yao  and
      Li, Kan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.668/",
    doi = "10.18653/v1/2025.findings-emnlp.668",
    pages = "12523--12533",
    ISBN = "979-8-89176-335-7",
    abstract = "We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize high-quality draft tokens without requiring auxiliary models or external databases. By dynamically analyzing structural patterns across parallel reasoning paths through a probabilistic aggregation mechanism, it identifies consensus token sequences that align with the decoding distribution. Evaluations on mathematical reasoning and code generation benchmarks demonstrate a substantial improvement in draft acceptance rates over baselines, while reducing the latency in draft token construction. This work establishes a paradigm shift for efficient multi-sample inference, enabling seamless integration of speculative decoding with sampling-based reasoning techniques."
}