Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process

Pre-trained language models (PLMs) leverage chains-of-thought (CoT) to simulate human reasoning and inference processes, achieving proficient performance in multi-hop QA. However, a gap persists between PLMs’ reasoning abilities and those of humans when tackling complex problems. Psychological studies suggest a vital connection between explicit information in input passages and human prior knowledge during reading. Nevertheless, current research has given less attention to linking input passages and PLMs’ pre-training-based knowledge derived from human reading processes. In this study, we introduce a prompting explicit and implicit knowledge (PEI) framework, which uses prompts to connect explicit and implicit knowledge, aligning with human reading process for multi-hop QA. We consider the input passages as explicit knowledge, using it to elicit implicit knowledge through unified prompt reasoning. Additionally, our model incorporates type-specific reasoning via prompts, a form of implicit knowledge. Experimental results show that PEI performs comparably to the state-of-the-art on HotpotQA. Ablation studies confirm the effectiveness of our model in bridging and incorporating explicit and implicit knowledge.