This research focuses on optimizing discrete prompts for large language models (LLMs) without needing access to the model's internal weights or gradients.
It uses differential privacy to obfuscate responses for queries that fall near a model's decision boundary. bdplarchive.rar
A more recent 2023 paper from (TMLR) uses the same acronym for Black-box Discrete Prompt Learning . This research focuses on optimizing discrete prompts for