Kavli Affiliate: Xiang Zhang | First 5 Authors: Tianchun Wang, Zichuan Liu, Yuanzhou Chen, Jonathan Light, Haifeng Chen | Summary: While increasing training compute has significantly improved the performance of large language models (LLMs), similar gains have not been observed when scaling inference compute. We hypothesize that the primary issue lies in the uniformity of […]
Continue.. Diversified Sampling Improves Scaling LLM inference