Evaluating the Correctness of Explainable AI Algorithms for Classification
Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of these algorithms as there is no "ground truth" in the existing datasets to validate their correctness. In this work, we develop a method to quantitatively evaluate the correctness of XAI algorithms by creating datasets with known explanation ground truth. To this end, we focus on the binary classification problems. String datasets are constructed using formal language derived from a grammar. A string is positive if and only if a certain property is fulfilled. Symbols serving as explanation ground truth in a positive string are part of an explanation if and only if they contributes to fulfilling the property. Two popular feature attribution explainers, Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), are used in our experiments.We show that: (1) classification accuracy is positively correlated with explanation accuracy; (2) SHAP provides more accurate explanations than LIME; (3) explanation accuracy is negatively correlated with dataset complexity.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationClassificationExplainable Artificial Intelligence (XAI)Feature ImportanceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, thereby combining classification and explanat…
On the stability, correctness and plausibility of visual explanation methods based on feature importance
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between th…
Feature ImportanceRule Learning by Modularity
In this paper, we present a modular methodology that combines state-of-the-art methods in (stochastic) machine learning with traditional methods in rule learning to provide efficient and scalable algorithms for the class…
On Evaluating Explainability Algorithms
A plethora of methods attempting to explain predictions of black-box models have been proposed by the Explainable Artificial Intelligence (XAI) community. Yet, measuring the quality of the generated explanations is large…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critical research topic. Traditional MD approa…
Binary Classification