paper-with-me

홈 › Papers

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

2025-03-07 · Simon A. Aytes, Jinheon Baek, Sung Ju Hwang

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.

📄 PDF Abstract BibTeX arXiv:2503.05179

Code (1)

simonaytes/sot 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought

2026-01-13 · Bowen Li, Ziqi Xu, Jing Ren, Renqiang Luo 외 arxiv

Despite notable advancements in prompting methods for Large Language Models (LLMs), such as Chain-of-Thought (CoT), existing strategies still suffer from excessive token usage and limited generalisability across diverse …

Computational Efficiency

SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models

2026-01-06 · Ruiyang Zhang, Dongzhan Zhou, Zhedong Zheng arxiv

Despite the empirical success of extensive, step-by-step reasoning in large multimodal models, long reasoning processes inevitably incur substantial computational overhead, i.e., in terms of higher token costs and increa…

Reinforcement Learning

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

2025-10-28 · Huanyu Zhang, Wenshan Wu, Chengzu Li, Ning Shang 외 arxiv

While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visua…

Multimodal Reasoning

ProofSketch: Efficient Verified Reasoning for Large Language Models

2025-10-28 · Disha Sheshanarayana, Tanishka Magar arxiv

Reasoning methods such as chain-of-thought prompting and self-consistency have shown immense potential to improve the accuracy of large language models across various reasoning tasks. However such methods involve generat…

CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning

2026-04-01 · Xudong Wang, Zilong Wang, Kui Su, Zhaoyan Ming arxiv

Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes tw…