paper-with-me

Papers

Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Data

2024-09-30 · Mythreyi Velmurugan, Chun Ouyang, Yue Xu, Renuka Sindhgatta, Bemali Wickramanayake, Catarina Moreira

Explainable Artificial Intelligence (XAI) techniques are used to provide transparency to complex, opaque predictive models. However, these techniques are often designed for image and text data, and it is unclear how fit-for-purpose they are when applied to tabular data. As XAI techniques are rarely evaluated in settings with tabular data, the applicability of existing evaluation criteria and methods are also unclear and needs (re-)examination. For example, some works suggest that evaluation methods may unduly influence the evaluation results when using tabular data. This lack of clarity on evaluation procedures can lead to reduced transparency and ineffective use of XAI techniques in real world settings. In this study, we examine literature on XAI evaluation to derive guidelines on functionally-grounded assessment of local, post hoc XAI techniques. We identify 20 evaluation criteria and associated evaluation methods, and derive guidelines on when and how each criterion should be evaluated. We also identify key research gaps to be addressed by future work. Our study contributes to the body of knowledge on XAI evaluation through in-depth examination of functionally-grounded XAI evaluation protocols, and has laid the groundwork for future research on XAI evaluation.

📄 PDF Abstract BibTeX arXiv:2410.12803

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Similar Papers 제목 키워드 기반

Evaluating Explainable Methods for Predictive Process Analytics: A Functionally-Grounded Approach

2020-12-08 · Mythreyi Velmurugan, Chun Ouyang, Catarina Moreira, Renuka Sindhgatta

Predictive process analytics focuses on predicting the future states of running instances of a business process. While advanced machine learning techniques have been used to increase accuracy of predictions, the resultin…

BIG-bench Machine LearningFeature ImportancePredictive Process Monitoring

SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach

2024-02-05 · Mohammad N. S. Jahromi, Satya. M. Muddamsetty, Asta Sofie Stage Jarlner, Anna Murphy Høgenhaug 외

Explainable AI (XAI) aids in deciphering 'black-box' models. While several methods have been proposed and evaluated primarily in the image domain, the exploration of explainability in the text domain remains a growing re…

Sentiment Analysis

Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

2026-08-18 · Ram Rachum, Yotam Amitai, Bálint Gyevnár, Reuth Mirsky 외 arxiv

This preliminary paper outlines a planned evaluation benchmark for Explainable Reinforcement Learning (XRL) methods. Current evaluations rely on functionally-grounded metrics like faithfulness and compactness, and on hum…

Reinforcement Learning

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods

2022-06-24 · Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus, Valerie Chen 외

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings ha…

Experimental DesignFraud Detection

Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method

2021-01-26 · Satya M. Muddamsetty, Mohammad N. S. Jahromi, Andreea E. Ciontos, Laura M. Fenoy 외

Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of "black-box" models. In this paper, a novel XAI visual explanation algorithm kn…

Adversarial AttackExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)