UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
This work addresses the need for interpretable and robust QA systems for users and researchers, but it is incremental as it builds on an existing platform with new features.
The paper tackles the problem of interpretability and robustness in question answering systems by introducing SQuARE v2, an infrastructure that provides explainability methods like saliency maps and graph-based explanations, along with adversarial attacks, to compare models and support research on trustworthy QA.
Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, which are difficult to interpret by humans. Inherently interpretable models or post hoc explainability methods can help users to comprehend how a model arrives at its prediction and, if successful, increase their trust in the system. Furthermore, researchers can leverage these insights to develop new methods that are more accurate and less biased. In this paper, we introduce SQuARE v2, the new version of SQuARE, to provide an explainability infrastructure for comparing models based on methods such as saliency maps and graph-based explanations. While saliency maps are useful to inspect the importance of each input token for the model's prediction, graph-based explanations from external Knowledge Graphs enable the users to verify the reasoning behind the model prediction. In addition, we provide multiple adversarial attacks to compare the robustness of QA models. With these explainability methods and adversarial attacks, we aim to ease the research on trustworthy QA models. SQuARE is available on https://square.ukp-lab.de.