The five Is: Key principles for interpretable and safe conversational AI

TL;DR

This paper proposes five key principles—interpretability, explainability, data independence, interactive learning, and inquisitiveness—for creating transparent, accountable, and safer conversational AI systems as alternatives to black box models.

Contribution

It introduces a set of five foundational principles aimed at developing interpretable and safe conversational AI, highlighting challenges and potential benefits over current black box approaches.

Findings

Five principles promote transparency and safety in conversational AI.

Implementing these principles can reduce failures of AI systems.

Challenges include technical and practical implementation issues.

Abstract

In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.