Explainable Goal Recognition: A Framework Based on Weight of Evidence
We introduce and evaluate an eXplainable Goal Recognition (XGR) model that uses the Weight of Evidence (WoE) framework to explain goal recognition problems. Our model provides human-centered explanations that answer why? and why not? questions. We computationally evaluate the performance of our system over eight different domains. Using a human behavioral study to obtain the ground truth from human annotators, we further show that the XGR model can successfully generate human-like explanations. We then report on a study with 60 participants who observe agents playing Sokoban game and then receive explanations of the goal recognition output. We investigate participants' understanding obtained by explanations through task prediction, explanation satisfaction, and trust.
Code (0)
등록된 구현이 없습니다.
Tasks
SokobanSimilar Papers 제목 키워드 기반
Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach
Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to th…
Decision MakingHuman Agent CollaborationSokobanRevealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues
Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. Current research predominantly treats personality recognition as a classification task, faili…
Personality Trait RecognitionIntegrating Evidence into the Design of XAI and AI-based Decision Support Systems: A Means-End Framework for End-users in Construction
A narrative review is used to develop a theoretical evidence-based means-end framework to build an epistemic foundation to uphold explainable artificial intelligence instruments so that the reliability of outcomes genera…
Decision MakingExplainable artificial intelligenceTowards Explainable Multimodal Depression Recognition for Clinical Interviews
Recently, multimodal depression recognition for clinical interviews (MDRC) has recently attracted considerable attention. Existing MDRC studies mainly focus on improving task performance and have achieved significant dev…
Decision MakingDepression DetectionExplainable artificial intelligenceMedical Diagnosis+3Multimodal Explanations: Justifying Decisions and Pointing to the Evidence
Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attention weights or text-based generation of …
Activity RecognitionExplainable ModelsQuestion AnsweringVisual Question Answering+1