Prompt Generation
Prompt generation focuses on automatically creating effective prompts for large language models (LLMs) to improve their performance on various downstream tasks. Current research emphasizes developing methods for generating prompts that are tailored to specific tasks and data, often employing reinforcement learning, evolutionary algorithms, or differentiable optimal transport to optimize prompt design. This area is significant because effective prompt engineering can unlock the full potential of LLMs, leading to improved performance in diverse applications such as text-to-image synthesis, question answering, and medical image analysis, while reducing the need for extensive fine-tuning.
Papers
Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example
Aven-Le Zhou, Yu-Ao Wang, Wei Wu, Kang Zhang
Prompt Learning on Temporal Interaction Graphs
Xi Chen, Siwei Zhang, Yun Xiong, Xixi Wu, Jiawei Zhang, Xiangguo Sun, Yao Zhang, Feng Zhao, Yulin Kang