@inproceedings{yu-etal-2025-accelerate,
    title = "Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence",
    author = "Yu, Yijiong  and
      Wang, Wei  and
      Chen, Ran  and
      Pei, Ji",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.457/",
    pages = "9018--9025",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and time-consuming. To address this inefficiency, we leverage the inherent parallelizability of certain tasks to accelerate the reasoning process. Specifically, when multiple parallel reasoning steps exist, we decode multiple tokens per forward pass via a tree-like attention mask within a single sequence, avoiding additional memory usage. Experimental results show that our method achieves up to nearly 100{\%} speedup in decoding while basically maintaining the answer quality. Our code is available in https://github.com/yuyijiong/parallel-decoding-in-one-sequence"
}