A Diagnostic Study of Explainability Techniques for Text Classification
Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models' predictions transparent have inspired an abundance of new explainability techniques. Provided with an already trained model, they compute saliency scores for the words of an input instance. However, there exists no definitive guide on (i) how to choose such a technique given a particular application task and model architecture, and (ii) the benefits and drawbacks of using each such technique. In this paper, we develop a comprehensive list of diagnostic properties for evaluating existing explainability techniques. We then employ the proposed list to compare a set of diverse explainability techniques on downstream text classification tasks and neural network architectures. We also compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones. Overall, we find that the gradient-based explanations perform best across tasks and model architectures, and we present further insights into the properties of the reviewed explainability techniques.
Code (1)
Tasks
ClassificationDiagnosticGeneral Classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification
Although explainability is essential in the clinical diagnosis, most deep learning models still function as black boxes without elucidating their decision-making process. In this study, we investigate the explainable mod…
Decision MakingDiagnosticimage-classificationImage Classification+3Applied Explainability for Large Language Models: A Comparative Study
Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, d…
The Susceptibility of Example-Based Explainability Methods to Class Outliers
This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as corr…
image-classificationImage Classificationtext-classificationText ClassificationEvaluating the Explainability of Vision Transformers in Medical Imaging
Understanding model decisions is crucial in medical imaging, where interpretability directly impacts clinical trust and adoption. Vision Transformers (ViTs) have demonstrated state-of-the-art performance in diagnostic im…
Image ClassificationAdvancing Histopathology-Based Breast Cancer Diagnosis: Insights into Multi-Modality and Explainability
It is imperative that breast cancer is detected precisely and timely to improve patient outcomes. Diagnostic methodologies have traditionally relied on unimodal approaches; however, medical data analytics is integrating …
Decision MakingDiagnostic