@inproceedings{aytes-etal-2025-sketch,
    title = "Sketch-of-Thought: Efficient {LLM} Reasoning with Adaptive Cognitive-Inspired Sketching",
    author = "Aytes, Simon A.  and
      Baek, Jinheon  and
      Hwang, Sung Ju",
    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/author-page-yu-wang-polytechnic/2025.emnlp-main.1236/",
    doi = "10.18653/v1/2025.emnlp-main.1236",
    pages = "24307--24331",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs, leading to increased computational overhead. We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints to reduce token usage while preserving reasoning accuracy. SoT is designed as a flexible, modular approach and is instantiated with three paradigms{---}Conceptual Chaining, Chunked Symbolism, and Expert Lexicons{---}each tailored to distinct reasoning tasks and selected dynamically at test-time by a lightweight routing model. Across 18 reasoning datasets spanning multiple domains, languages, and modalities, SoT achieves token reductions of up to 84{\%} with minimal accuracy loss. In tasks such as mathematical and multi-hop reasoning, it even improves accuracy while shortening outputs."
}