
AI
Temperature Scaling and Beam Search Text Generation in LLMs, for the ML-Adjacent
What “temperature” is, how it works, its relationship to the beam search heuristic, and how LLM output generation can still go haywire Mike Cvet · Follow Published in Towards Data Science · 19 min read · 9 hours ago — Photo by Paul Green on Unsplash; all other images by author unless otherwise noted If you’ve spent any time with APIs for LLMs like those from OpenAI or Anthropic, you’ll have seen the temperature setting