AI RESEARCH
On Meta-Prompting
arXiv CS.AI
•
ArXi:2312.06562v4 Announce Type: replace-cross Modern large language models (LLMs) are capable of interpreting input strings as instructions, or prompts, and carry out tasks based on them. Unlike traditional learners, LLMs cannot use back-propagation to obtain feedback, and condition their output in situ in a phenomenon known as in-context learning (ICL). Many approaches to prompting and pre-