Fractional Reasoning in LLMs: A New Way to Control Inference Depth

Fractional Reasoning in LLMs: A New Way to Control Inference Depth

What is included in this article:The limitations of current test-time compute strategies in LLMs.Introduction of Fractional Reasoning (FR) as a training-free, model-agnostic framework.Techniques for latent state manipulation using reasoning prompts and adjustable scaling.Breadth- and depth-based scaling benefits demonstrated across GSM8K, MATH500, and GPQA.Evaluation results showing FR’s superiority over Best-of-N and Majority Vote.Analysis of F…