The goal of Explainable AI (XAI) is to design methods to provide insights into the reasoning process of black-box models, such as deep neural networks, in order to explain them to humans. Social science research states that such explanations should be conversational, similar to human-to-human explanations. In this work, we show how to incorporate XAI in a conversational agent, using a standard design for the agent comprising natural language understanding and generation components. We build upon an XAI question bank, which we extend by quality-controlled paraphrases, to understand the user's information needs. We further systematically survey the literature for suitable explanation methods that provide the information to answer those questions, and present a comprehensive list of suggestions. Our work is the first step towards truly natural conversations about machine learning models with an explanation agent. The comprehensive list of XAI questions and the corresponding explanation methods may support other researchers in providing the necessary information to address users' demands. To facilitate future work, we release our source code and data.
Painting the black box white: experimental findings from applying XAI to an ECG reading setting
University of Milano-Bicocca(米兰比可卡大学);University of Siena(锡耶纳大学)
从符号AI系统到黑盒、子符号和统计AI系统的转变促使人们对可解释AI(XAI)的兴趣迅速增加,即使黑盒AI系统可解释给人类决策者的方法,目的是使这些系统更容易接受,更有用的工具和支持。然而,我们提出的观点是,而不是总是使黑盒透明,这些方法是在\emph{painting the black boxes white}的风险,从而无法提供一个透明的水平,将增加系统的可用性和可理解性,或者,甚至在产生新的错误,在我们所谓的\emph{white-box paradox}的风险。为了解决这些可用性相关的问题,在这项工作中,我们专注于用户的认知层面的解释和XAI系统。为此,我们设计并进行了一项基于心电图的实验,其中44名心脏病住院医生和专家参与了一项人工智能支持的心电图阅读任务。在此过程中,我们调查了不同的研究问题,涉及用户特征(例如专业知识)与他们对AI和XAI系统的感知之间的关系,包括他们的信任,感知解释的质量和他们将决策过程推迟到自动化(即技术主导)的倾向,以及这些不同维度之间的相互关系。我们的研究结果提供了一个贡献的评估基于人工智能的支持系统从人与人工智能互动为导向的角度,并奠定了基础,为进一步调查XAI及其对决策和用户体验的影响。
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
Phenikaa University(菲卡大学);Phenikaa School of Computing(菲卡计算机学院);MobiFone Corporation(MobiFone集团);MobiFone HighTech Center(MobiFone高科技中心);National Economics University(国民经济大学);College of Technology(技术学院)
LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces
Khmelnytskyi National University(赫梅利尼茨基国立大学);Taras Shevchenko National University of Kyiv(基辅塔拉斯·舍甫琴科国立大学);V.M. Glushkov Institute of Cybernetics of NAS of Ukraine(乌克兰国家科学院V.M.格卢什科夫控制论研究所)
Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentation
Lebanese University(黎巴嫩大学);National Center for Remote Sensing - CNRS, Lebanon(国家遥感中心 - 法国国家科学研究中心(黎巴嫩));Center for Digital Systems, IMT Nord Europe, Institut Mines-Télécom, University of Lille(数字系统中心,IMT Nord Europe,矿业电信学院,里尔大学)
Scrutinizing XAI using linear ground-truth data with suppressor variables
Technische Universität Berlin(柏林工业大学);Eindhoven University of Technology(埃因霍温理工大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所(BIFOLD));Korea University(高丽大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);Physikalisch-Technische Bundesanstalt(德国联邦物理技术研究院);Charité – Universitätsmedizin Berlin(柏林夏里特医学院)
A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language
Andalusian Research Institute in Data Science and Computational Intelligence(数据科学与计算智能安达卢西亚研究机构);Universidad de Granada(格拉纳达大学);Department of Computer Science(计算机科学系);Artificial Intelligence Lab(人工智能实验室);Vrije Universiteit Brussel(布鲁塞尔自由大学)