Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
This work addresses the need for more reliable and scalable reasoning in large language models, though it appears incremental as it builds on existing chain-of-thought methods.
The paper tackled the problem of improving zero-shot chain-of-thought prompting by addressing limitations like human expertise requirements and inaccuracies, resulting in a method that outperforms existing strategies across four reasoning benchmarks.
Chain-of-thought (CoT) prompting has significantly enhanced the capability of large language models (LLMs) by structuring their reasoning processes. However, existing methods face critical limitations: handcrafted demonstrations require extensive human expertise, while trigger phrases are prone to inaccuracies. In this paper, we propose the Zero-shot Uncertainty-based Selection (ZEUS) method, a novel approach that improves CoT prompting by utilizing uncertainty estimates to select effective demonstrations without needing access to model parameters. Unlike traditional methods, ZEUS offers high sensitivity in distinguishing between helpful and ineffective questions, ensuring more precise and reliable selection. Our extensive evaluation shows that ZEUS consistently outperforms existing CoT strategies across four challenging reasoning benchmarks, demonstrating its robustness and scalability.