Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses visual queries to help users refine prompts without extensive writing. Our technical contribution is a formulation of interactive intent inference under an information-theoretic framework. APE represents latent user intent as interpretable feature requirements using language model priors, adaptively generates visual queries, and compiles elicited requirements into effective prompts. Evaluation on IDEA-Bench and DesignBench shows that APE achieves stronger alignment with improved efficiency. A user study with 128 participants on user-defined tasks demonstrates 19.8% higher perceived alignment without increased workload. Our work contributes a principled approach to prompting that offers an effective and efficient complement to the prevailing prompt-based interaction paradigm with text-to-image models.
@article{arxiv.2602.04713,
title = {Adaptive Prompt Elicitation for Text-to-Image Generation},
author = {Xinyi Wen and Lena Hegemann and Xiaofu Jin and Shuai Ma and Antti Oulasvirta},
journal= {arXiv preprint arXiv:2602.04713},
year = {2026}
}