@inproceedings{liu-etal-2026-think-faster,
    title = "Think Faster Than Words: Efficient {LLM} Chain-of-Thought Reasoning via Dynamic Shortcut Decoding",
    author = "Liu, Fan  and
      Wang, Yanhao  and
      Zhang, Min  and
      Chen, Zhikang  and
      Li, Zeyuan  and
      He, Lewei  and
      Pan, Jiahui",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1330/",
    pages = "28825--28836",
    ISBN = "979-8-89176-390-6",
    abstract = "This paper proposes shortcut decoding, an efficient framework for accelerating Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs). Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. Motivated by the observation that LLMs frequently converge to correct solutions internally before completing explicit textual reasoning, we propose a dual-signal adaptive controller that integrates lightweight probes over internal hidden states with step-level entropy. This controller detects convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. Experiments across multiple mathematical reasoning benchmarks demonstrate that shortcut decoding reduces token usage by approximately 35{\%}, maintains accuracy comparable to full CoT decoding, and achieves final-answer accuracy comparable to the full CoT baseline, outperforming existing early-stopping methods without updating the base model. Our code is available at https://github.com/kuromi9527/shortcut{\_}decoding."
}