Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
Shanu Kumar, Saish Mendke, Karody Lubna Abdul Rahman, Santosh Kurasa, Parag Agrawal, Sandipan Dandapat
Abstract
Chain-of-thought (CoT) prompting has significantly enhanced the 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.
BibTeX
@inproceedings{kumar-etal-2025-enhancing,
title = "Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection",
author = "Kumar, Shanu and
Mendke, Saish and
Rahman, Karody Lubna Abdul and
Kurasa, Santosh and
Agrawal, Parag and
Dandapat, Sandipan",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.137/",
pages = "2003--2025"
}