Finding Uncommon Ground: A Human-Centered Model for Extrospective Explanations

TL;DR

This paper introduces a human-centered, personalized explanation model for AI that adapts to individual user preferences and context, aiming to improve understanding and relevance of AI explanations.

Contribution

It presents a novel model of AI explanations that personalizes information based on user preferences and interaction history, emphasizing a human-centered approach.

Findings

Proposes a dynamic memory model for personalized explanations

Enhances relevance of AI explanations for non-expert users

Supports tailored communication based on user context

Abstract

The need for explanations in AI has, by and large, been driven by the desire to increase the transparency of black-box machine learning models. However, such explanations, which focus on the internal mechanisms that lead to a specific output, are often unsuitable for non-experts. To facilitate a human-centered perspective on AI explanations, agents need to focus on individuals and their preferences as well as the context in which the explanations are given. This paper proposes a personalized approach to explanation, where the agent tailors the information provided to the user based on what is most likely pertinent to them. We propose a model of the agent's worldview that also serves as a personal and dynamic memory of its previous interactions with the same user, based on which the artificial agent can estimate what part of its knowledge is most likely new information to the user.