Chain of Thought Prompting Elicits Knowledge Augmentation
This addresses the challenge of integrating domain knowledge into deep models for reasoning tasks, offering a more efficient approach compared to conventional methods.
The paper tackles the problem of knowledge augmentation in deep learning by proposing CoT-KA, a Chain-of-Thought-based method that eliminates the need for external knowledge retrieval or reasoning models, and it outperforms pure CoT and non-augmented methods on most of eleven benchmarks for reasoning tasks.
The knowledge-augmented deep learning paradigm refers to a paradigm in which domain knowledge is identified and integrated into deep models. Conventional methods typically employ task-specific approaches to gather external knowledge from various sources. In contrast, large language models are extensively pre-trained and can serve as a comprehensive source of external knowledge. In this paper, we propose CoT-KA, a Chain-of-Thought-based method that augments knowledge for deep learning. CoT-KA avoids the need for additional knowledge retrieval or knowledge reasoning models, as required in conventional augmentation methods. Our results demonstrate that CoT-KA outperforms both pure CoT-based methods and the non-augmented method across the majority of eleven publicly available benchmarks for various reasoning tasks.