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

TL;DR

This paper introduces the PEI framework that enhances multi-hop question answering by linking explicit passage information with implicit knowledge through prompts, inspired by human reading processes, achieving competitive results.

Contribution

The study proposes a novel PEI prompting framework that explicitly connects explicit and implicit knowledge, aligning with human cognition, to improve multi-hop QA performance.

Findings

PEI achieves comparable results to state-of-the-art on HotpotQA.

Ablation studies validate the effectiveness of explicit-implicit knowledge integration.

PEI demonstrates the importance of human-inspired reasoning in QA models.

Abstract

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 passages and human prior knowledge during reading. Nevertheless, current research has given insufficient attention to linking input passages and PLMs' pre-training-based knowledge from the perspective of human cognition studies. 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, employing them to elicit implicit knowledge through unified prompt reasoning. Furthermore, 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 efficacy of our model in bridging and integrating explicit and implicit knowledge.