Guardado en:
Detalles Bibliográficos
Autores principales: Sithakoul, Samuel, Meftah, Sara, Feutry, Clément
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.19897
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914891477024768
author Sithakoul, Samuel
Meftah, Sara
Feutry, Clément
author_facet Sithakoul, Samuel
Meftah, Sara
Feutry, Clément
contents Recent research in explainability has given rise to numerous post-hoc attribution methods aimed at enhancing our comprehension of the outputs of black-box machine learning models. However, evaluating the quality of explanations lacks a cohesive approach and a consensus on the methodology for deriving quantitative metrics that gauge the efficacy of explainability post-hoc attribution methods. Furthermore, with the development of increasingly complex deep learning models for diverse data applications, the need for a reliable way of measuring the quality and correctness of explanations is becoming critical. We address this by proposing BEExAI, a benchmark tool that allows large-scale comparison of different post-hoc XAI methods, employing a set of selected evaluation metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19897
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BEExAI: Benchmark to Evaluate Explainable AI
Sithakoul, Samuel
Meftah, Sara
Feutry, Clément
Machine Learning
Artificial Intelligence
Computation and Language
Recent research in explainability has given rise to numerous post-hoc attribution methods aimed at enhancing our comprehension of the outputs of black-box machine learning models. However, evaluating the quality of explanations lacks a cohesive approach and a consensus on the methodology for deriving quantitative metrics that gauge the efficacy of explainability post-hoc attribution methods. Furthermore, with the development of increasingly complex deep learning models for diverse data applications, the need for a reliable way of measuring the quality and correctness of explanations is becoming critical. We address this by proposing BEExAI, a benchmark tool that allows large-scale comparison of different post-hoc XAI methods, employing a set of selected evaluation metrics.
title BEExAI: Benchmark to Evaluate Explainable AI
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2407.19897