Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviews
This work addresses the problem of balancing accuracy and interpretability for developers and users in NLP applications, but it is incremental as it builds on existing discussions with a specific case study.
The study tackled the trade-off between model interpretability and performance by comparing black-box and interpretable models for inferring ratings from reviews, introducing a Composite Interpretability score to quantify this relationship and finding that performance generally improves with decreased interpretability, though not monotonically.
Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model performance has sparked discussions around the deployment of AI, particularly in critical applications where knowing the rationale of decision-making is essential for trust and accountability. In this study, we conduct a comparative analysis of several black-box and interpretable models, focusing on a specific NLP use case that has received limited attention: inferring ratings from reviews. Through this use case, we explore the intricate relationship between the performance and interpretability of different models. We introduce a quantitative score called Composite Interpretability (CI) to help visualize the trade-off between interpretability and performance, particularly in the case of composite models. Our results indicate that, in general, the learning performance improves as interpretability decreases, but this relationship is not strictly monotonic, and there are instances where interpretable models are more advantageous.