Papers by Corentin Boidot
HAL (Le Centre pour la Communication Scientifique Directe), Apr 14, 2023
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific r... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers.
HAL (Le Centre pour la Communication Scientifique Directe), Apr 14, 2023
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific r... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers.
HAL (Le Centre pour la Communication Scientifique Directe), Dec 14, 2023
EXplainable AI (XAI) offers a wide range of algorithmic solutions to the problem of AI's opacity,... more EXplainable AI (XAI) offers a wide range of algorithmic solutions to the problem of AI's opacity, but ensuring of their usefulness remains a challenge. In this study, we propose an multi-explanation XAI system using surrogate rules, LIME and nearest neighbor on a random forest. Through an experiment in an e-sports prediction task, we demonstrate the feasibility and measure the usefulness of working with multiple forms of explanation. Considering users' preferences, we offer new perspectives for XAI design and evaluation, highlighting the concept of data difficulty and of the idea of prior agreement between users and AI.
Communications in computer and information science, 2023
EXplainable AI (XAI) was created to address the issue of Machine Learning's lack of transparency.... more EXplainable AI (XAI) was created to address the issue of Machine Learning's lack of transparency. Its methods are expanding, as are the ways of evaluating them, including human performance-based evaluations of explanations. These evaluations allow us to quantify the contribution of XAI algorithms to human decision-making. This work performs accuracy and response time measurements to evaluate SHAP explanations on an e-sports prediction task. The results of this pilot experiment contradict our intuitions about the beneficial potential of these explanations and allow us to discuss the difficulties of this evaluation methodology.
Communications in Computer and Information Science
EXplainable AI (XAI) was created to address the issue of Machine Learning's lack of transparency.... more EXplainable AI (XAI) was created to address the issue of Machine Learning's lack of transparency. Its methods are expanding, as are the ways of evaluating them, including human performance-based evaluations of explanations. These evaluations allow us to quantify the contribution of XAI algorithms to human decision-making. This work performs accuracy and response time measurements to evaluate SHAP explanations on an e-sports prediction task. The results of this pilot experiment contradict our intuitions about the beneficial potential of these explanations and allow us to discuss the difficulties of this evaluation methodology.
Uploads
Papers by Corentin Boidot