Designing a Rashomon Machine: Pluri-perspectivism and XAI for Creativity Support

TL;DR

The paper introduces Pluri-perspectivism as a novel framework for explainable AI, enhancing human-machine creative collaboration by enabling exploration of multiple perspectives and bridging epistemological gaps.

Contribution

It proposes a new framework for XAI called Pluri-perspectivism, adapting the Rashomon Technique to support embodied creativity and human agency in co-creative systems.

Findings

Facilitates exploring a spectrum of creative possibilities

Reintroduces productive friction in human-machine collaboration

Bridges epistemological gap between human and machine

Abstract

While intelligent technologies offer unique opportunities for creativity support, there are fundamental challenges in designing human-centered co-creative systems. Explainable AI (XAI) can contribute when shifting its traditional role from justification (explaining decisions) to exploration (explaining possibilities). Contextual understanding is essential for supporting embodied creativity. Generative Artificial Intelligence (AI) models are fundamentally limited, however, by their reliance on disembodied data. We propose Pluri-perspectivism as a framework for XAI, to bridge the epistemological gap between human and machine, and promote creative exploration. It is a pragmatic, action-oriented solution to guide the system, repurposing XAI methods such as the Rashomon Technique. This facilitates exploring a spectrum of creative possibilities, and the exchange of 'perspectives' between human and machine. Using Pluri-perspectivism as a framework for XAI, we can reintroduce productive friction and support human agency in human-machine creative collaborations.