ConstitutionalExperts: Training a Mixture of Principle-based Prompts

arXiv:2403.04894v1 Announce Type: new
Abstract: Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce ConstitutionalExperts, a method for learning a prompt consisting of constitutional principles (i.e. rules), given a training dataset. Unlike prior methods that optimize the prompt as a single entity, our method incrementally improves the prompt by surgically editing individual principles. We also show that we …

abstract arxiv cs.ai cs.cl dataset language language models large language large language models llms process prompt prompts rules tasks training type work writing