Exploring LLMs: Applications in Text-Based Games & Interactive Storytelling

Language models, specifically large language models (LLMs), have been making waves in the artificial intelligence industry. With the ability to generate human-like text, LLMs have found a niche in applications such as text-based games and interactive storytelling. This article will introduce LLMs, discuss their potential applications in these areas, and explore how they are transforming the gaming and storytelling landscape.

What are LLMs?

Large language models are advanced AI systems that have been trained on vast amounts of text data. These models are capable of understanding and generating human-like text by predicting the most likely next word or phrase in a given context. Some popular LLMs include OpenAI's GPT-3 and Google's BERT.

Applications in Text-Based Games

Text-based games, also known as interactive fiction, have been around since the early days of computing. These games rely on text input from the player and text output from the game, creating an immersive and engaging experience. LLMs can be employed in various aspects of text-based games, including:

1. Dynamic Game Content

LLMs can be used to generate dynamic game content, such as descriptions, conversations, and storylines. By leveraging the language model's understanding of context and narrative structure, developers can create unique experiences for each player, keeping the game fresh and engaging.

2. Improved NPC Interactions

Non-player characters (NPCs) are a staple in many games, often providing crucial information and assistance to the player. With LLMs, NPCs can engage in more natural and nuanced conversations, reacting to player input in a way that feels more human-like. This can create a deeper sense of immersion and connection between the player and the game world.

3. Procedurally Generated Stories

LLMs can generate entire storylines, quests, and adventures on-the-fly by understanding the context of the game world and the player's actions. This allows for virtually limitless content, as each playthrough can present a unique story and experience for the player.

Applications in Interactive Storytelling

Interactive storytelling is a form of narrative that allows the audience to actively participate and influence the story's outcome. LLMs can greatly enhance interactive storytelling experiences by providing:

1. Adaptive Narratives

LLMs can adapt the story based on the reader's choices and preferences, creating a personalized narrative experience. This can lead to a greater sense of engagement and investment in the story.

2. Natural Language Interface

LLMs can serve as a natural language interface for interactive storytelling, allowing readers to interact with the story using everyday language. This makes the experience more accessible and engaging, as readers do not need to learn specific commands or syntax.

3. Collaborative Storytelling

LLMs can assist writers in creating interactive narratives by suggesting possible story branches, character developments, and plot twists based on the writer's input. This can help writers overcome writer's block and explore new creative directions.


Large language models have the potential to revolutionize text-based games and interactive storytelling by providing more dynamic, engaging, and immersive experiences for players and readers. As AI continues to advance, we can expect even more innovative applications and exciting developments in these fields.

An AI coworker, not just a copilot

View VelocityAI