XPROAX-Local explanations for text classification with progressive neighborhood approximation
The importance of the neighborhood for training a local surrogate model to approximate the local decision boundary of a black box classifier has been already highlighted in the literature. Several attempts have been made to construct a better neighborhood for high dimensional data, like texts, by using generative autoencoders. However, existing approaches mainly generate neighbors by selecting purely at random from the latent space and struggle under the curse of dimensionality to learn a good local decision boundary. To overcome this problem, we propose a progressive approximation of the neighborhood using counterfactual instances as initial landmarks and a careful 2-stage sampling approach to refine counterfactuals and generate factuals in the neighborhood of the input instance to be explained. Our work focuses on textual data and our explanations consist of both word-level explanations from the original instance (intrinsic) and the neighborhood (extrinsic) and factual- and counterfactual-instances discovered during the neighborhood generation process that further reveal the effect of altering certain parts in the input text. Our experiments on real-world datasets demonstrate that our method outperforms the competitors in terms of usefulness and stability (for the qualitative part) and completeness, compactness and correctness (for the quantitative part).
Code (1)
Tasks
Classificationcounterfactualtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Explaining text classifiers through progressive neighborhood approximation with realistic samples
The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood quality for high-dimensional data, for …
Extending Logic Explained Networks to Text Classification
Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular d…
ClassificationSensitivitytext-classificationText ClassificationLLM-Based Visual Explanation Evaluation Framework for Assessing the Explainability of Facial Skin Disease Classification Models
This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing Grad-CAM explanations in facial skin disease diagnosis models. While previous studies have primarily focused on improv…
Clinical KnowledgePrompt EngineeringData AugmentationComparing Automatic and Human Evaluation of Local Explanations for Text Classification
Text classification models are becoming increasingly complex and opaque, however for many applications it is essential that the models are interpretable. Recently, a variety of approaches have been proposed for generatin…
General ClassificationRecommendation Systemstext-classificationText ClassificationEvaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction
Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs o…