Using Games to Learn How Large Language Models Work

TL;DR

This paper introduces two educational games designed to teach the principles of how large language models (LLMs) operate, aiming to improve AI literacy through interactive learning.

Contribution

The paper presents novel game-based tools that demonstrate key concepts of LLM training and text generation, enhancing understanding of complex AI systems.

Findings

Games effectively illustrate LLM training on datasets.

Games demonstrate word-by-word text generation process.

Early-stage prototypes with potential for educational impact.

Abstract

While artificial intelligence (AI) technology is becoming increasingly popular, its underlying mechanisms tend to remain opaque to most people. To address this gap, the field of AI literacy aims to develop various resources to teach people how AI systems function. Here we contribute to this line of work by proposing two games that demonstrate principles behind how large language models (LLMs) work and use data. The first game, Learn Like an LLM, aims to convey that LLMs are trained to predict sequences of text based on a particular dataset. The second game, Tag-Team Text Generation, focuses on teaching that LLMs generate text one word at a time, using both predicted probabilities of the data and randomness. While the games proposed are still in early stages and would benefit greatly from further discussion, we hope they can contribute to using game-based learning to teach about complex AI systems like LLMs.