Go to ACL ARR 2025 May homepageSketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
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 15 reasoning datasets spanning multiple domains, languages, and modalities, SoT achieves token reductions of up to 78% with minimal accuracy loss. In tasks such as mathematical and multi-hop reasoning, it even improves accuracy while shortening outputs.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: prompting,reasoning
Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency
Languages Studied: English, German, Italian, Korean
Submission Number: 93
Loading