Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation

TL;DR

Luminate is a framework and interactive system that enables users to systematically explore, evaluate, and synthesize a vast design space generated by large language models, enhancing human-AI co-creation in creative tasks.

Contribution

The paper introduces a novel framework and system for structured exploration of LLM-generated design spaces, addressing limitations of current interaction paradigms.

Findings

Users can explore a broader range of ideas with Luminate.

The system improves creative productivity for professional writers.

Participants found the structured exploration beneficial for idea synthesis.

Abstract

Thanks to their generative capabilities, large language models (LLMs) have become an invaluable tool for creative processes. These models have the capacity to produce hundreds and thousands of visual and textual outputs, offering abundant inspiration for creative endeavors. But are we harnessing their full potential? We argue that current interaction paradigms fall short, guiding users towards rapid convergence on a limited set of ideas, rather than empowering them to explore the vast latent design space in generative models. To address this limitation, we propose a framework that facilitates the structured generation of design space in which users can seamlessly explore, evaluate, and synthesize a multitude of responses. We demonstrate the feasibility and usefulness of this framework through the design and development of an interactive system, Luminate, and a user study with 14 professional writers. Our work advances how we interact with LLMs for creative tasks, introducing a way to harness the creative potential of LLMs.