I recently co-authored a research paper on The Benefits of a Concise Chain-of-Thought on Problem-Solving in Large Language Models.
It discusses how using an LLM using a concise chain-of-thought (CCoT) prompt reduces its verbosity, cost, and response time without negative impacts on its performance in MCQA problem-solving tasks.
A pre-print version of the paper is now available on arXiv at: http://arxiv.org/abs/2401.05618