Self-Explanation in Social AI Agents

TL;DR

This paper introduces a self-explanation method for social AI agents using introspection over a self-model, enhancing transparency and trust in social interactions, with evaluation and deployment in educational settings.

Contribution

It presents a novel self-explanation approach leveraging introspection, Chain of Thought, and ChatGPT to improve transparency of social AI agents.

Findings

Self-explanations are evaluated for completeness and correctness.

The method is successfully deployed in a live educational class.

The approach enhances transparency and trust in social AI interactions.

Abstract

Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspection over a self-model of an AI social assistant. The self-model is captured as a functional model that specifies how the methods of the agent use knowledge to achieve its tasks. The process of generating self-explanations uses Chain of Thought to reflect on the self-model and ChatGPT to provide explanations about its functioning. We evaluate the self-explanation of the AI social assistant for completeness and correctness. We also report on its deployment in a live class.