Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations
Sperrle, Fabian, El-Assady, Mennatallah, Guo, Grace, Chau, Duen Horng, Endert, Alex, Keim, Daniel
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Sep-14-2020
- Country:
- North America
- United States
- New York > New York County
- New York City (0.15)
- Massachusetts > Suffolk County
- Boston (0.04)
- California > Santa Clara County
- San Jose (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- New York > New York County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- United Kingdom > Scotland
- City of Glasgow > Glasgow (0.04)
- Middle East > Cyprus
- United Kingdom > Scotland
- North America
- Genre:
- Overview (1.00)
- Research Report > Experimental Study (0.49)
- Industry:
- Health & Medicine (0.68)
- Technology: