Concept

Training-Free Methods for Scaling LLM Reasoning

Training-free methods enhance the reasoning of Large Language Models without altering their pre-trained parameters. These techniques are applied during inference and primarily involve two approaches: using sophisticated prompting strategies, such as Chain-of-Thought, and employing algorithmic control, like search algorithms, to direct the model's reasoning.

0

1

Updated 2026-05-06

Contributors are:

Who are from:

Tags

Ch.5 Inference - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences