Open-Domain Question Answering (ODQA) systems necessitate a reader model capable of generating answers by simultaneously referring to multiple passages. Although representative models like Fusion-in-Decoder (FiD) have been proposed to address this challenge, these systems can inadvertently rely on spurious features instead of genuine causal relationships between the question and the passages to generate answers. To counter this problem, we introduce the Rational Fusion-in-Decoder (RFiD) model. Our model leverages the encoders of FiD to differentiate between causal relationships and spurious features, subsequently guiding the decoder to generate answers informed by this discernment. Experimental results on two ODQA datasets, Natural Questions (NQ) and TriviaQA (TQ), demonstrate that our model surpasses previous methods, achieving improvements of up to 1.5 and 0.7 in Exact Match scores on NQ, and exhibits an enhanced ability to identify causal relationships.

翻译：开放域问答系统需要一种能够同时参考多个段落生成答案的阅读器模型。尽管诸如融合解码器（Fusion-in-Decoder, FiD）等代表性模型已被提出以应对这一挑战，但这些系统可能会无意中依赖虚假特征而非问题与段落之间的真实因果关联来生成答案。为解决该问题，我们提出了理性融合解码器（Rational Fusion-in-Decoder, RFiD）模型。该模型利用FiD的编码器区分因果关联与虚假特征，进而引导解码器基于这种辨识结果生成答案。在Natural Questions (NQ) 和 TriviaQA (TQ) 两个开放域问答数据集上的实验表明，我们的模型超越了以往方法，在NQ数据集上的精确匹配得分提升了最多1.5和0.7，并展现出更强的因果关联识别能力。