Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs

TL;DR

This study demonstrates that affordable, fine-tuned smaller LLMs outperform larger generic models in answering course-specific MCQs, offering a resource-efficient approach for educational applications.

Contribution

It introduces a publicly available MCQ dataset and shows that textbook-based fine-tuning of smaller LLMs improves accuracy over larger pre-trained models.

Findings

Smaller fine-tuned models outperform larger generic models in MCQ accuracy.

Fine-tuning with course textbooks enhances model performance.

Quantisation reduces resource usage without significantly compromising accuracy.

Abstract

In education, the capability of generating human-like text of Large Language Models (LLMs) inspired work on how they can increase the efficiency of learning and teaching. We study the affordability of these models for educators and students by investigating how LLMs answer multiple-choice questions (MCQs) with respect to hardware constraints and refinement techniques. We explore this space by using generic pre-trained LLMs (the 7B, 13B, and 70B variants of LLaMA-2) to answer 162 undergraduate-level MCQs from a course on Programming Languages (PL) -- the MCQ dataset is a contribution of this work, which we make publicly available. Specifically, we dissect how different factors, such as using readily-available material -- (parts of) the course's textbook -- for fine-tuning and quantisation (to decrease resource usage) can change the accuracy of the responses. The main takeaway is that smaller textbook-based fine-tuned models outperform generic larger ones (whose pre-training requires conspicuous resources), making the usage of LLMs for answering MCQs resource- and material-wise affordable.