Use of a generative chatbot as a middleman to improve User Experience in Interactive Fiction games

• Adriano Tolfo Dotta UNIPAMPA
• Marcelo Resende Thielo UNIPAMPA
• Jean Felipe Patikowski Cheiran UNIPAMPA

DOI: https://doi.org/10.5753/sbgames_estendido.2023.234160

Resumo

In the 1970s and 1980s, interactive fiction games emerged and changed the gaming world by enabling players to talk to the machine, make their own decisions, choose their paths, and decide what to collect and do. This freedom captivated players, but at the time, games were limited by programmed scripts that only accepted words present in the game’s code dictionary in a limited format, usually two or three keywords by phrase. However, technological advances have paved the way for improvements in this regard, replacing scripts with artificial intelligence using APIs, such as ChatGPT, for example. Thus, it may be possible to offer players an even more natural and customized experience, where each decision is more flexible with the player’s writing style. In this work, we carried out a communication experiment with the ChatGPT as an intermediary for interactive fiction games and the Frotz game interpreter (a modified version of the Z-Machine interpreter) to assess the feasibility of the approach.

Referências

Biswas, S. (2023). Role of chatgpt in gaming: According to chatgpt.

Griffith, D. and Jokisch, S. (2016). Frotz - a portable z-machine interpreter.

Hausknecht, M., Ammanabrolu, P., Côté, M.-A., and Yuan, X. (2020). Interactive fiction games: A colossal adventure. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):7903–7910.

Montfort, N. (2011). Twisty Little Passages: An Approach to Interactive Fiction. MIT Press, Cambridge, MA, USA.

OpenAI (2020). OpenAI API. [link].

Tan, Q., Kazemi, A., and Mihalcea, R. (2023). Text-based games as a challenging benchmark for large language models.

Trivedi, K. (2023). Creating a personalized text-based adventure game with chatgpt api: A step-by-step guide to crafting dynamic narratives.

Tsai, C. F., Zhou, X., Liu, S. S., Li, J., Yu, M., and Mei, H. (2023). Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions. [link].

Wu, T., He, S., Liu, J., Sun, S., Liu, K., Han, Q.-L., and Tang, Y. (2023). A brief overview of chatgpt: The history, status quo and potential future development. IEEE/CAA Journal of Automatica Sinica, 10(5):1122–1136.