Chain of Thought Prompting Elicits Knowledge Augmentation

TL;DR

This paper introduces CoT-KA, a chain-of-thought prompting method that enhances deep learning models with external knowledge without needing additional retrieval or reasoning modules, improving performance on reasoning benchmarks.

Contribution

The paper presents a novel knowledge augmentation method using chain-of-thought prompting that eliminates the need for external knowledge retrieval or reasoning models.

Findings

CoT-KA outperforms pure CoT-based methods on multiple benchmarks.

CoT-KA surpasses non-augmented models in reasoning tasks.

The approach simplifies knowledge integration in deep learning.

Abstract

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.