ORIBA: Exploring LLM-Driven Role-Play Chatbot as a Creativity Support Tool for Original Character Artists

2025-12-14

AI Summary

This study addresses the risk of diminished artistic agency when generative AI intervenes in visual art creation. We propose a “non-visual, concept-centric” AI collaboration paradigm and introduce ORIBA—a role-playing chatbot designed for original character (OC) artists. Built upon large language models, ORIBA implements a character-driven dialogue mechanism wherein conceptual design—e.g., backstory, personality, and narrative context—serves as the exclusive collaborative domain, while strictly preserving visual authorship with the human artist. Through user-centered design and qualitative human-AI interaction research involving 14 practicing artists, our evaluation demonstrates significant improvements in imaginative engagement, multidimensional character attribute construction, affective bonding with OCs, and subsequent motivation for visual realization. This work constitutes the first systematic articulation of design principles that uphold creative agency; it offers a reusable, cross-modal collaborative framework for AI-augmented creative practice.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Intelligent Robots: Embodied AI

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advances in Generative AI (GAI) have led to new opportunities for creativity support. However, this technology has raised ethical concerns in the visual artists community. This paper explores how GAI can assist visual artists in developing original characters (OCs) while respecting their creative agency. We present ORIBA, an AI chatbot leveraging large language models (LLMs) to enable artists to role-play with their OCs, focusing on conceptualization (e.g., backstories) while leaving exposition (visual creation) to creators. Through a study with 14 artists, we found ORIBA motivated artists' imaginative engagement, developing multidimensional attributes and stronger bonds with OCs that inspire their creative process. Our contributions include design insights for AI systems that develop from artists' perspectives, demonstrating how LLMs can support cross-modal creativity while preserving creative agency in OC art. This paper highlights the potential of GAI as a neutral, non-visual support that strengthens existing creative practice, without infringing artistic exposition.

Problem

• Explores GAI's role in assisting original character artists
• Presents ORIBA chatbot for role-play to develop character concepts
• Investigates preserving creative agency while using LLMs for creativity support

Innovation

• LLM-driven chatbot for character role-play
• Focuses on conceptualization, not visual creation
• Preserves artistic agency in creative process