The Density of Thought: Predicting and Steering Reasoning in Large Language Models
We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a controllable inference-time target. We prompt frozen pretrained models to solve problems via CoT and measure the density of each reasoning step with two independent metric...
Tanush Kalhan, Anupam Chattopadhyay, Sriram Ranga et al.
· 0 citations