Prompt Evolution for Generative AI: A Classifier-Guided Approach

arXiv:2305.16347v2 Announce Type: replace-cross Abstract: Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fail to connect the generated outputs and desired target concepts/preferences implied by the prompts. Current research addressing this limitation has largely focused on enhancing the prompts before output generation or improving the model's performance up front. I