论文标题
DISENTQA：通过反事实问题解开参数和上下文知识回答
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering
论文作者
论文摘要
问题回答模型通常可以在推理时间内访问两个“知识”的来源：（1）参数知识 - 模型权重中编码的事实知识，以及（2）上下文知识 - 外部知识（例如，给出的Wikipedia段落）给了模型，以生成基础答案。将这两个知识来源纠缠在一起是生成质量检查模型的核心问题，因为尚不清楚答案是否源于给定的非参数知识。这种不持久性对信任，可解释性和事实的问题有影响。在这项工作中，我们提出了一个新的范式，其中训练了质量检查模型以解开两种知识来源。使用反事实数据增强，我们介绍了一个模型，该模型可以预测一个给定问题的两个答案：一个基于给定的上下文知识，一个基于参数知识。我们对自然问题数据集的实验表明，这种方法通过使它们对两个知识源之间的知识冲突更加牢固，同时产生有用的分离答案，从而提高了质量检查模型的性能。
Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e.g., a Wikipedia passage) given to the model to generate a grounded answer. Having these two sources of knowledge entangled together is a core issue for generative QA models as it is unclear whether the answer stems from the given non-parametric knowledge or not. This unclarity has implications on issues of trust, interpretability and factuality. In this work, we propose a new paradigm in which QA models are trained to disentangle the two sources of knowledge. Using counterfactual data augmentation, we introduce a model that predicts two answers for a given question: one based on given contextual knowledge and one based on parametric knowledge. Our experiments on the Natural Questions dataset show that this approach improves the performance of QA models by making them more robust to knowledge conflicts between the two knowledge sources, while generating useful disentangled answers.
