Abstract
Game mechanics can be viewed in terms of affordances: possible actions offered by the environment—depending on the agent (e.g., in a fantasy role-playing game, a sword can be wielded by a knight, but probably not by a dragon). Recently, text generated by large language models (LLMs) has been used to create open-ended text-based game content. However, LLMs have been shown to generate sexist text when trained on gender-biased data. If bias manifests in educational text game affordances it could harm goal achievement. We examine binary gender biases in LIGHT, an English-language persona-based dataset for researching language grounded in a fantasy adventure world, training LLMs on LIGHT and analyzing the diversity of affordances in quests. We find male characters have a more diverse space of affordances yet are less diverse in practice (e.g., mostly wielding a sword) in original and generated quests. To gauge impact on gameplay, we create games from LIGHT quests which can be played in the TextWorld research framework. Artificial agents trained only on male games significantly outperform female, suggesting an impact of affordance biases. These findings illustrate risks in AI- or data-driven generation of serious game content where gender is involved: overlooked biases in affordances can propagate, autonomously enforcing harmful, stereotypical behaviors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
huggingface.co/facebook/bart-base/.
- 3.
Seeds are numbers used to initialize random number generators.
- 4.
References
Ahn, M., et al.: Do as I Can, Not as I Say: Grounding Language in Robotic Affordances. arXiv preprint arXiv:2204.01691 (2022)
Ammanabrolu, P., Jia, R., Riedl, M.: Situated dialogue learning through procedural environment generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (2022)
Ammanabrolu, P., Urbanek, J., Li, M., Szlam, A., Rocktäschel, T., Weston, J.: How to motivate your dragon: teaching goal-driven agents to speak and act in fantasy worlds. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (2021)
Côté, M.A., et al.: TextWorld: A Learning Environment for Text-based Games. In: CGW@IJCAI (2018)
Dinan, E., Fan, A., Williams, A., Urbanek, J., Kiela, D., Weston, J.: Queens are powerful too: mitigating gender bias in dialogue generation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (2020)
Fernández Galeote, D., et al.: The good, the bad, and the divergent in game-based learning: player experiences of a serious game for climate change engagement. In: Proceedings of the 25th International Academic Mindtrek Conference, pp. 256–267 (2022)
Fulda, N., Ricks, D., Murdoch, B., Wingate, D.: What can you do with a rock? Affordance extraction via word embeddings. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 1039–1045 (2017)
Garner, J.: The cross-sectional development of verb-noun collocations as constructions in L2 writing. Int. Rev. Appl. Linguist. Lang. Teach. 60(3), 909–935 (2020)
Gibson, J.J.: The theory of affordances. Hilldale, USA 1(2), 67–82 (1977)
Glăveanu, V.P.: A sociocultural theory of creativity: bridging the social, the material, and the psychological. Rev. Gen. Psychol. 24(4), 335–354 (2020)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
McClelland, T., Sliwa, P.: Gendered affordance perception and unequal domestic labour. Philos. Phenomenological Res. 107(20), 501–524 (2022)
Nguyen, C.T.: Games and the art of agency. Philos. Rev. 128(4), 423–462 (2019)
Protopsaltis, A., Pannese, L., Hetzner, S., Pappa, D., de Freitas, S.: Creative learning with serious games. Int. J. Emerg. Technol. Learn. (iJET) 5(2010), 4–6 (2010)
Ulmer, D., Hardmeier, C., Frellsen, J.: deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks. arXiv preprint arXiv:2204.06815 (2022)
Urbanek, J., et al.: Learning to speak and act in a fantasy text adventure game. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (2019)
Vargha, A., Delaney, H.D.: A critique and improvement of the “CL” common language effect size statistics of McGraw and Wong. J. Educ. Behav. Stat. 25(2), 101–132 (2000)
Xinogalos, S., Satratzemi, M.: The use of educational games in programming assignments: SQL Island as a case study. Appl. Sci. 12(13), 6563 (2022)
Yao, S., Rao, R., Hausknecht, M., Narasimhan, K.: Keep CALM and explore: language models for action generation in text-based games. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
McGuire, E.S., Tomuro, N. (2024). What Can You Do with a Sword? Gender Biases in Text Game Affordances. In: Dondio, P., et al. Games and Learning Alliance. GALA 2023. Lecture Notes in Computer Science, vol 14475. Springer, Cham. https://doi.org/10.1007/978-3-031-49065-1_48
Download citation
DOI: https://doi.org/10.1007/978-3-031-49065-1_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49064-4
Online ISBN: 978-3-031-49065-1
eBook Packages: Computer ScienceComputer Science (R0)