Memory networks for consumer protection:unfairness exposed
This work addresses the need for explainable AI in consumer protection, though it appears incremental by adapting existing memory network techniques to a specific domain.
The paper tackled the problem of poor explainability in data-driven AI methods for consumer protection by using legal rationales in memory-augmented neural networks, resulting in improved classification accuracy and meaningful natural language explanations.
Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents. However, a shortcoming of data-driven approaches is poor explainability. We posit that in this domain useful explanations of classifier outcomes can be provided by resorting to legal rationales. We thus consider several configurations of memory-augmented neural networks where rationales are given a special role in the modeling of context knowledge. Our results show that rationales not only contribute to improve the classification accuracy, but are also able to offer meaningful, natural language explanations of otherwise opaque classifier outcomes.