Lengthening the reasoning steps in prompts improves the reasoning abilities of large language models (LLMs), while shortening the steps diminishes their abilities. Incorrect rationales can still yield favorable outcomes if they maintain the required length of inference. The advantages of increasing reasoning steps are task-dependent.

https://arxiv.org/abs//2401.04925

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers