Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?
This is an incremental opinion piece that calls for clearer criteria and evaluation methods for interpretability in NLP, aimed at researchers and practitioners in the field.
The paper tackles the problem of defining and evaluating faithfulness in interpretable NLP systems, arguing that current binary definitions are unrealistic and proposing a graded approach for more practical utility.
With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. But what is interpretability, and what constitutes a high-quality interpretation? In this opinion piece we reflect on the current state of interpretability evaluation research. We call for more clearly differentiating between different desired criteria an interpretation should satisfy, and focus on the faithfulness criteria. We survey the literature with respect to faithfulness evaluation, and arrange the current approaches around three assumptions, providing an explicit form to how faithfulness is "defined" by the community. We provide concrete guidelines on how evaluation of interpretation methods should and should not be conducted. Finally, we claim that the current binary definition for faithfulness sets a potentially unrealistic bar for being considered faithful. We call for discarding the binary notion of faithfulness in favor of a more graded one, which we believe will be of greater practical utility.