Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e.g., replacing key question entities or shuffling table columns. To systematically study the robustness of Table QA models, we propose a benchmark called RobuT, which builds upon existing Table QA datasets (WTQ, WikiSQL-Weak, and SQA) and includes human-annotated adversarial perturbations in terms of table header, table content, and question. Our results indicate that both state-of-the-art Table QA models and large language models (e.g., GPT-3) with few-shot learning falter in these adversarial sets. We propose to address this problem by using large language models to generate adversarial examples to enhance training, which significantly improves the robustness of Table QA models. Our data and code is publicly available at https://github.com/yilunzhao/RobuT.
@article{arxiv.2306.14321,
title = {RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations},
author = {Yilun Zhao and Chen Zhao and Linyong Nan and Zhenting Qi and Wenlin Zhang and Xiangru Tang and Boyu Mi and Dragomir Radev},
journal= {arXiv preprint arXiv:2306.14321},
year = {2023}
}