Towards Reconciling Usability and Usefulness of Explainable AI Methodologies
Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and accountability issues when they produce an incorrect decision. Explainable AI (XAI) seeks to bridge the knowledge gap, between developers and end-users, by offering insights into how an AI algorithm functions. Many modern algorithms focus on making the AI model "transparent", i.e. unveil the inherent functionality of the agent in a simpler format. However, these approaches do not cater to end-users of these systems, as users may not possess the requisite knowledge to understand these explanations in a reasonable amount of time. Therefore, to be able to develop suitable XAI methods, we need to understand the factors which influence subjective perception and objective usability. In this paper, we present a novel user-study which studies four differing XAI modalities commonly employed in prior work for explaining AI behavior, i.e. Decision Trees, Text, Programs. We study these XAI modalities in the context of explaining the actions of a self-driving car on a highway, as driving is an easily understandable real-world task and self-driving cars is a keen area of interest within the AI community. Our findings highlight internal consistency issues wherein participants perceived language explanations to be significantly more usable, however participants were better able to objectively understand the decision making process of the car through a decision tree explanation. Our work also provides further evidence of importance of integrating user-specific and situational criteria into the design of XAI systems. Our findings show that factors such as computer science experience, and watching the car succeed or fail can impact the perception and usefulness of the explanation.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingExplainable Artificial Intelligence (XAI)Self-Driving CarsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations
We establish, from the point of view of Explainable AI (XAI), connections between Consistency-Based Diagnosis (CBD), on one side, and Actual Causality and Causal Responsibility, on the other. CBD has received little atte…
Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree o…
ArticlescounterfactualExplainable artificial intelligenceLet's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (X…
counterfactualDecision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Explainable Artificial Intelligence Recommendation System by Leveraging the Semantics of Adverse Childhood Experiences: Proof-of-Concept Prototype Development
The study of adverse childhood experiences and their consequences has emerged over the past 20 years. In this study, we aimed to leverage explainable artificial intelligence, and propose a proof-of-concept prototype for …
Explainable artificial intelligenceGraph GenerationQuestion AnsweringOn Bootstrapping Machine Learning Performance Predictors via Analytical Models
Performance modeling typically relies on two antithetic methodologies: white box models, which exploit knowledge on system's internals and capture its dynamics using analytical approaches, and black box techniques, which…
BIG-bench Machine Learning