Preference-Guided Prompt Optimization for Text-to-Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917274043023360 |
|---|---|
| author | Li, Zhipeng Liao, Yi-Chi Holz, Christian |
| author_facet | Li, Zhipeng Liao, Yi-Chi Holz, Christian |
| contents | Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt refinement tools heavily rely on human effort, while prompt optimization methods focus on numerical functions and are not designed for human-centered generative tasks, where feedback is better expressed as binary preferences and demands convergence within few iterations. We present APPO, a preference-guided prompt optimization algorithm. Instead of iterating prompts, users only provide binary preferential feedback. APPO adaptively balances its strategies between exploiting user feedback and exploring new directions, yielding effective and efficient optimization. We evaluate APPO on image generation, and the results show APPO enables achieving satisfactory outcomes in fewer iterations with lower cognitive load than manual prompt editing. We anticipate APPO will advance human-AI collaboration in generative tasks by leveraging user preferences to guide complex content creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13131 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Preference-Guided Prompt Optimization for Text-to-Image Generation Li, Zhipeng Liao, Yi-Chi Holz, Christian Human-Computer Interaction Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt refinement tools heavily rely on human effort, while prompt optimization methods focus on numerical functions and are not designed for human-centered generative tasks, where feedback is better expressed as binary preferences and demands convergence within few iterations. We present APPO, a preference-guided prompt optimization algorithm. Instead of iterating prompts, users only provide binary preferential feedback. APPO adaptively balances its strategies between exploiting user feedback and exploring new directions, yielding effective and efficient optimization. We evaluate APPO on image generation, and the results show APPO enables achieving satisfactory outcomes in fewer iterations with lower cognitive load than manual prompt editing. We anticipate APPO will advance human-AI collaboration in generative tasks by leveraging user preferences to guide complex content creation. |
| title | Preference-Guided Prompt Optimization for Text-to-Image Generation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.13131 |