Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold
This highlights a systemic issue in NLP that could lead to false conclusions and unwise choices, urging the community to adopt more multi-dimensional approaches.
The paper identifies a 'square one bias' in NLP research, where experiments typically focus on optimizing accuracy for English data while neglecting other dimensions like fairness or interpretability, and shows through manual classification that most work explores only one dimension at a time, limiting exploration of the research space.
The prototypical NLP experiment trains a standard architecture on labeled English data and optimizes for accuracy, without accounting for other dimensions such as fairness, interpretability, or computational efficiency. We show through a manual classification of recent NLP research papers that this is indeed the case and refer to it as the square one experimental setup. We observe that NLP research often goes beyond the square one setup, e.g, focusing not only on accuracy, but also on fairness or interpretability, but typically only along a single dimension. Most work targeting multilinguality, for example, considers only accuracy; most work on fairness or interpretability considers only English; and so on. We show this through manual classification of recent NLP research papers and ACL Test-of-Time award recipients. Such one-dimensionality of most research means we are only exploring a fraction of the NLP research search space. We provide historical and recent examples of how the square one bias has led researchers to draw false conclusions or make unwise choices, point to promising yet unexplored directions on the research manifold, and make practical recommendations to enable more multi-dimensional research. We open-source the results of our annotations to enable further analysis at https://github.com/google-research/url-nlp