Journal article
Knowledge-based XAI through CBR: There is more to explanations than models can tell
23 Aug 2021
Abstract
The underlying hypothesis of knowledge-based explainable artificial
intelligence is the data required for data-centric artificial intelligence
agents (e.g., neural networks) are less diverse in contents than the data
required to explain the decisions of such agents to humans. The idea is that a
classifier can attain high accuracy using data that express a phenomenon from
one perspective whereas the audience of explanations can entail multiple
stakeholders and span diverse perspectives. We hence propose to use domain
knowledge to complement the data used by agents. We formulate knowledge-based
explainable artificial intelligence as a supervised data classification problem
aligned with the CBR methodology. In this formulation, the inputs are case
problems composed of both the inputs and outputs of the data-centric agent and
case solutions, the outputs, are explanation categories obtained from domain
knowledge and subject matter experts. This formulation does not typically lead
to an accurate classification, preventing the selection of the correct
explanation category. Knowledge-based explainable artificial intelligence
extends the data in this formulation by adding features aligned with domain
knowledge that can increase accuracy when selecting explanation categories.
Metrics
1 Record Views
Details
- Title
- Knowledge-based XAI through CBR: There is more to explanations than models can tell
- Creators
- Rosina WeberManil ShresthaAdam J Johs
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Information Science (Informatics)
- Identifiers
- 991019174556204721