Dynamics of LLM beliefs during chain-of-thought reasoning – Baram Sosis – PIBBSS Symposium



This video was recorded during the 2024 PIBBSS Symposium. Read more about it on our website:
https://pibbss.ai/symposium-24/

About the talk:
Chain-of-thought and other forms of scaffolding can significantly enhance the capabilities of language models, making a better understanding of how they work an important goal for safety research. Benchmark accuracy can measure how much scaffolding improves performance, but this does not give us insight into how the LLMs arrive at their answers. I will present the results of my work studying how the internal beliefs of LLMs of different sizes evolve over the course of chain-of-thought reasoning as measured by linear probes.

source

3 thoughts on “Dynamics of LLM beliefs during chain-of-thought reasoning – Baram Sosis – PIBBSS Symposium”

Leave a Comment