# UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA

arXiv: https://arxiv.org/abs/2208.09316 · HTML: https://mlsanity.com/paper/2208.09316/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 19 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models](https://mlsanity.com/paper/1909.09251/) (2019)
- [TWEAC: Transformer with Extendable QA Agent Classifiers](https://mlsanity.com/paper/2104.07081/) (2021)
- [MetaQA: Combining Expert Agents for Multi-Skill Question Answering](https://mlsanity.com/paper/2112.01922/) (2021)
- [UKP-SQUARE: An Online Platform for Question Answering Research](https://mlsanity.com/paper/2203.13693/) (2022)
- [Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models](https://mlsanity.com/paper/2102.08239/) (2021)

## Built on by (most cited first, 2 of 2)

- [UKP-SQuARE v3: A Platform for Multi-Agent QA Research](https://mlsanity.com/paper/2303.18120/) (2023)
- [UKP-SQuARE: An Interactive Tool for Teaching Question Answering](https://mlsanity.com/paper/2305.19748/) (2023)

## Abstract (arXiv)

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.