It’s Not Just the Prompt: Model Choice Dominates LLM Creative Output
Open Access
- 13 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Abstract
No abstract availableFunding Information
- BMFTR (16DII133)
- MATH+ (EXC-2046/1, project id 390685689)
- Einstein Foundation Berlin (EPP-2019-524)
- German Research Foundation (DFG) (496119880 (VisualMine))
- German Research Foundation (DFG) (531115272 (ProImpact))
- German Research Foundation (DFG) (SFB 1404/2 (FONDA))
This publication has 14 references indexed in Scilit:
- Has the creativity of large-language models peaked?Journal of Creativity, 2025
- ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing2024
- From Prompt Engineering to Collaborating: A Human-Centered Approach to AI InterfacesInteractions, 2024
- Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts2023
- Design Guidelines for Prompt Engineering Text-to-Image Generative Models2022
- PromptMaker: Prompt-based Prototyping with Large Language Models2022
- On the Dangers of Stochastic Parrots2021
- Experiments with More Than One Random Factor: Designs, Analytic Models, and Statistical PowerAnnual Review of Psychology, 2017
- Treating stimuli as a random factor in social psychology: A new and comprehensive solution to a pervasive but largely ignored problem.Journal of Personality and Social Psychology, 2012
- Divergence measures based on the Shannon entropyIEEE Transactions on Information Theory, 1991