PRewrite: Prompt Rewriting with Reinforcement Learning

arXiv:2401.08189v2 Announce Type: replace-cross
Abstract: Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion. This manual procedure can be time consuming, ineffective, and the generated prompts are, in a lot of cases, sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications?
To address these questions, in this paper, we investigate prompt engineering …

abstract applications arxiv cases cs.ai cs.cl cs.lg development engineering error fashion generated llm prompt prompts reinforcement reinforcement learning type work