Few shot and Chain-of-Thought prompting have shown promise when applied to Physics Question Answering Tasks, but are limited by the lack of mathematical ability inherent to LLMs, and are prone to hallucination. By utilizing a Mixture of Experts (MoE) Model, along with analogical prompting, we are able to show improved model performance when compared to the baseline on standard LLMs. We also survey the limits of these prompting techniques and the effects they have on model performance. Additionally, we propose Analogical CoT prompting, a prompting technique designed to allow smaller, open source models to leverage Analogical prompting, something they have struggled with, possibly due to a lack of specialist training data.
@article{arxiv.2412.05023,
title = {Steps are all you need: Rethinking STEM Education with Prompt Engineering},
author = {Krishnasai Addala and Kabir Dev Paul Baghel and Navya Gupta and Rishitej Reddy Vyalla and Chhavi Kirtani and Avinash Anand and Rajiv Ratn Shah},
journal= {arXiv preprint arXiv:2412.05023},
year = {2025}
}