Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations
arXiv:2009.06433
Abstract
This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches. These dimensions enable a descriptive characterization, facilitating comparisons between different study designs. They further structure the design space of XAI, converging towards a precise terminology required for a rigorous study of XAI. Our literature review differentiates between comparative studies and application papers, revealing methodological differences between the fields of machine learning, human-computer interaction, and visual analytics. Generally, each of these disciplines targets specific parts of the XAI process. Bridging the resulting gaps enables a holistic evaluation of XAI in real-world scenarios, as proposed by our conceptual model characterizing bias sources and trust-building. Furthermore, we identify and discuss the potential for future work based on observed research gaps that should lead to better coverage of the proposed model.
18pages, 2 figures, 2 tables
References in corpus (8)
- Towards A Rigorous Science of Interpretable Machine Learning
- RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
- explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
- Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
- Metrics for Explainable AI: Challenges and Prospects
- GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
- Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences
- Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics