CREATE: Testing LLMs for Associative Creativity

TL;DR

CREATE is a benchmark for evaluating large language models' ability to perform associative reasoning by generating diverse, specific paths connecting concepts, aiming to measure creative capacity objectively.

Contribution

The paper introduces CREATE, a novel benchmark for assessing models' associative creativity, emphasizing diversity, specificity, and the capacity to generate multiple meaningful connections.

Findings

Stronger models produce more diverse and specific paths.

High multiplicity of answers makes saturation difficult.

Creative prompting yields limited improvements.

Abstract

A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate models' capacity for creative associative reasoning. CREATE requires models to generate sets of paths connecting concepts in a model's parametric knowledge. Paths should have high specificity (distinctiveness and closeness of the concept connection) and high diversity (dissimilarity from other paths), and models are scored more highly if they produce a larger set of strong, diverse paths. This task shares demands of real creativity tasks like hypothesis generation, including an extremely large search space, but enables collection of a sizable benchmark with objective answer grading. Evaluation of frontier models shows that the strongest models achieve higher creative utility than others, with the high multiplicity of answers and complexity of the search making benchmark saturation difficult to achieve. Furthermore, our results illustrate that thinking models are not always more effective on our task, even with high token budgets. Recent approaches for creative prompting give some but limited additional improvement. CREATE provides a sandbox for developing new methods to improve models' capacity for associative creativity.