Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
This addresses the need for better evaluation of reasoning skills in multi-hop QA models, though it is incremental as it builds on prior dataset efforts.
The authors tackled the problem of lacking comprehensive reasoning explanations and true multi-hop requirements in existing multi-hop QA datasets by creating 2WikiMultiHopQA, a new dataset using structured and unstructured data with evidence information, which they demonstrated is challenging and ensures multi-hop reasoning is required.
A multi-hop question answering (QA) dataset aims to test reasoning and inference skills by requiring a model to read multiple paragraphs to answer a given question. However, current datasets do not provide a complete explanation for the reasoning process from the question to the answer. Further, previous studies revealed that many examples in existing multi-hop datasets do not require multi-hop reasoning to answer a question. In this study, we present a new multi-hop QA dataset, called 2WikiMultiHopQA, which uses structured and unstructured data. In our dataset, we introduce the evidence information containing a reasoning path for multi-hop questions. The evidence information has two benefits: (i) providing a comprehensive explanation for predictions and (ii) evaluating the reasoning skills of a model. We carefully design a pipeline and a set of templates when generating a question-answer pair that guarantees the multi-hop steps and the quality of the questions. We also exploit the structured format in Wikidata and use logical rules to create questions that are natural but still require multi-hop reasoning. Through experiments, we demonstrate that our dataset is challenging for multi-hop models and it ensures that multi-hop reasoning is required.