Enregistré dans:
Détails bibliographiques
Auteurs principaux: Geheeb, Julian, Ivan, Farhan Abid, Dyrda, Daniel, Anschütz, Miriam, Groh, Georg
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.24730
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910230587113472
author Geheeb, Julian
Ivan, Farhan Abid
Dyrda, Daniel
Anschütz, Miriam
Groh, Georg
author_facet Geheeb, Julian
Ivan, Farhan Abid
Dyrda, Daniel
Anschütz, Miriam
Groh, Georg
contents Recent research has demonstrated that large language models (LLMs) can support experts across various domains, including game design. In this study, we examine the utility of medium-sized LLMs, models that operate on consumer-grade hardware typically available in small studios or home environments. We began by identifying ten key aspects that contribute to a strong game concept and used ChatGPT to generate thirty sample game ideas. Three medium-sized LLMs, LLaMA 3.1, Qwen 2.5, and DeepSeek-R1, were then prompted to evaluate these ideas according to the previously identified aspects. A qualitative assessment by two researchers compared the models' outputs, revealing that DeepSeek-R1 produced the most consistently useful feedback, despite some variability in quality. To explore real-world applicability, we ran a pilot study with ten students enrolled in a storytelling course for game development. At the early stages of their own projects, students used our prompt and DeepSeek-R1 to refine their game concepts. The results indicate a positive reception: most participants rated the output as high quality and expressed interest in using such tools in their workflows. These findings suggest that current medium-sized LLMs can provide valuable feedback in early game design, though further refinement of prompting methods could improve consistency and overall effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24730
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs
Geheeb, Julian
Ivan, Farhan Abid
Dyrda, Daniel
Anschütz, Miriam
Groh, Georg
Human-Computer Interaction
Recent research has demonstrated that large language models (LLMs) can support experts across various domains, including game design. In this study, we examine the utility of medium-sized LLMs, models that operate on consumer-grade hardware typically available in small studios or home environments. We began by identifying ten key aspects that contribute to a strong game concept and used ChatGPT to generate thirty sample game ideas. Three medium-sized LLMs, LLaMA 3.1, Qwen 2.5, and DeepSeek-R1, were then prompted to evaluate these ideas according to the previously identified aspects. A qualitative assessment by two researchers compared the models' outputs, revealing that DeepSeek-R1 produced the most consistently useful feedback, despite some variability in quality. To explore real-world applicability, we ran a pilot study with ten students enrolled in a storytelling course for game development. At the early stages of their own projects, students used our prompt and DeepSeek-R1 to refine their game concepts. The results indicate a positive reception: most participants rated the output as high quality and expressed interest in using such tools in their workflows. These findings suggest that current medium-sized LLMs can provide valuable feedback in early game design, though further refinement of prompting methods could improve consistency and overall effectiveness.
title Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.24730