论文标题
反事实多人质量质量质量检查：一种减少断开推理的原因效应方法
Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning
论文作者
论文摘要
多跳质量质量检查需要对多个支持事实进行推理才能回答问题。但是，现有的质量检查模型始终依赖捷径，例如，仅通过一个事实提供真实答案，而不是多跳上的推理，这被称为$ \ textit {descontit {descontecon {descontect coniceing} $问题。为了减轻这个问题，我们提出了一种新颖的反事实多ihop质量质量质量质量质量质量质量检查，这是一种因果效应的方法，使能够减少断开的推理。它建立在因果关系的明确建模的基础上：1）断开推理的直接因果关系和2）从总因果效应中真正多跳的推理的因果效应。使用因果图，提出了一种反事实推断，以将脱节的推理与总因果效应相关，这为我们提供了一种新的观点和技术，以学习一种质量保证模型，以利用真正的多跳高推理而不是快捷方式。在基准HOTPOTQA数据集上进行了广泛的实验，该实验表明，该方法可以在减少断开推理方面取得显着改善。例如，我们的方法通过真实的多主推理获得了hotpotqa的Supp $ _s $得分的5.8％。该代码可在补充材料中找到。
Multi-hop QA requires reasoning over multiple supporting facts to answer the question. However, the existing QA models always rely on shortcuts, e.g., providing the true answer by only one fact, rather than multi-hop reasoning, which is referred as $\textit{disconnected reasoning}$ problem. To alleviate this issue, we propose a novel counterfactual multihop QA, a causal-effect approach that enables to reduce the disconnected reasoning. It builds upon explicitly modeling of causality: 1) the direct causal effects of disconnected reasoning and 2) the causal effect of true multi-hop reasoning from the total causal effect. With the causal graph, a counterfactual inference is proposed to disentangle the disconnected reasoning from the total causal effect, which provides us a new perspective and technology to learn a QA model that exploits the true multi-hop reasoning instead of shortcuts. Extensive experiments have conducted on the benchmark HotpotQA dataset, which demonstrate that the proposed method can achieve notable improvement on reducing disconnected reasoning. For example, our method achieves 5.8% higher points of its Supp$_s$ score on HotpotQA through true multihop reasoning. The code is available at supplementary material.
