Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (24) · 25985-25993
DOI: 10.1609/aaai.v39i24.34793 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yufeng Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).
Abstract (Originalsprache)
Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised CoT methods primarily select examples based on the semantics of the questions, which can introduce noise and lack interpretability. In this paper, we propose leveraging reasoning patterns to enhance CoT prompting effectiveness. Reasoning patterns represent the process by which language models arrive at their final results. By utilizing prior knowledge and prompt-based methods from large models, we first construct task-specific pattern sets. We then select diverse demonstrations based on different reasoning patterns. This approach not only mitigates the impact of noise but also provides explicit interpretability to help us understand the mechanisms of CoT. Extensive experiments demonstrate that our method is more robust and consistently leads to improvements across various reasoning tasks.
Zitieren
APA
Zhang, Y., Wang, X., Wu, L., & Wang, J. (2025). Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25985-25993. https://doi.org/10.1609/aaai.v39i24.34793
Vancouver
Zhang Y, Wang X, Wu L, Wang J. Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(24):25985-25993. doi:10.1609/aaai.v39i24.34793
BibTeX
@article{Zhang2025,
author = {Zhang, Yufeng and Wang, Xuepeng and Wu, Lingxiang and Wang, Jinqiao},
title = {Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {24},
pages = {25985--25993},
doi = {10.1609/aaai.v39i24.34793}
}
EUVIMED