Effective Representation to Capture Collaboration Behaviors between Explainer and User

TL;DR

This paper introduces a framework for interacting with explainable AI models using natural language, aiming to improve transparency and understanding of deep learning predictions.

Contribution

It presents a novel generic framework enabling natural language interactions with XAI models, enhancing interpretability and user collaboration.

Findings

Framework facilitates natural language communication with XAI models

Improves transparency and user understanding of AI predictions

Applicable to various deep learning models

Abstract

An explainable AI (XAI) model aims to provide transparency (in the form of justification, explanation, etc) for its predictions or actions made by it. Recently, there has been a lot of focus on building XAI models, especially to provide explanations for understanding and interpreting the predictions made by deep learning models. At UCLA, we propose a generic framework to interact with an XAI model in natural language.