Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process
This work addresses multi-hop question answering for natural language processing applications, but it is incremental as it builds on existing prompting and reasoning methods.
The authors tackled the gap between pre-trained language models' reasoning abilities and human reasoning in multi-hop question answering by introducing a Prompting Explicit and Implicit knowledge (PEI) framework that connects explicit information from passages with implicit knowledge through prompts, achieving performance comparable to state-of-the-art on HotpotQA.
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.