Reseach Article
Prompting Creativity: Analyzing the Impact of Prompt Engineering Philosophies on AI Gameplay in Codenames
| Journal of Advanced Artificial Intelligence |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 2 - Number 3 |
| Year of Publication: 2025 |
| Authors: Aditya Patil, Zeeshan Ahmad, Prashanth Reddy, Apurva Shrivastava, Ganesh Bankey |
10.5120/jaai202556
|
Aditya Patil, Zeeshan Ahmad, Prashanth Reddy, Apurva Shrivastava, Ganesh Bankey . Prompting Creativity: Analyzing the Impact of Prompt Engineering Philosophies on AI Gameplay in Codenames. Journal of Advanced Artificial Intelligence. 2, 3 ( Dec 2025), 29-35. DOI=10.5120/jaai202556
Abstract
The question is whether prompt engineering significantly impacts the creative reasoning of Large Language Models (LLMs) like GPT-4 and Gemini 2.5, moving beyond just factual accuracy to influence how models abstract, associate, and communicate concepts, as demonstrated in the wordassociation game Codenames. The aim is to see if prompt engineering can unlock the creativity within the objective framework of Codenames. The study evaluates the performance of models using various metrics and prompt engineering styles. The study, which introduced three philosophies (Spectrum Lens, Three Bridges, and Role Shifting), found that structured prompting acts as a cognitive scaffold rather than merely a linguistic interface, fundamentally altering the style and strategy of gameplay without necessarily increasing overall accuracy; specifically, structured guidance boosted Gemini 2.5’s conceptual depth and riskawareness while making GPT-4’s creativity more balanced but less spontaneous, suggesting that prompt design reconfigures how LLMs conceptualize and act in complex reasoning tasks. Overall, it is seen that prompt engineering does not have a substantial impact on the creativity aspect of LLMs, but some metrics do shift when LLMs are prompted.
References
- Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., and Steinhardt, J. 2021. Measuring Massive Multitask Language Understanding. arXiv preprint arXiv:2009.03300.
- Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., Hesse, C., and Schulman, J. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168.
- Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, Y., Narayanan, D., Wu, Y., Kumar, A., Newman, B., Yuan, B., Yan, B., Zhang, C., Cosgrove, C., Manning, C. D., R´e, C., and others. 2022. Holistic Evaluation of Language Models. arXiv preprint arXiv:2211.09110.
- Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., and others. 2022. Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models. arXiv preprint arXiv:2206.04615.
- Zhong, W., Cui, R., Guo, Y., Liang, Y., Lu, S., Wang, Y., Saied, A., Chen, W., and Duan, N. 2023. AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models. arXiv preprint arXiv:2304.06364.
- Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv preprint arXiv:2201.11903.
- Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M.,Wu, J.,Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877-1901.
- Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., and Neubig, G. 2023. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Computing Surveys 55, 9, 1-35.
- Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., and Hassabis, D. 2016. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature 529, 7587, 484-489.
- FAIR Team at Meta AI. 2022. Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning. Science 378, 6624, 1067-1074.
- Fan, L.,Wang, G., Jiang, Y., Mandlekar, A., Yang, Y., Zhu, H., Tang, A., Huang, D., Zhu, Y., and Anandkumar, A. 2022. Mine- Dojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge. In Advances in Neural Information Processing Systems.
- Boden, M. A. 2004. The Creative Mind: Myths and Mechanisms, 2nd edition. Psychology Press.
- Guilford, J. P. 1967. The Nature of Human Intelligence. McGraw-Hill.
- Mednick, S. A. 1962. The Associative Basis of the Creative Process. Psychological Review 69, 3, 220-232.
- Csikszentmihalyi, M. 1996. Creativity: Flow and the Psychology of Discovery and Invention. Harper Collins.
- Torrance, E. P. 1966. Torrance Tests of Creative Thinking. Personnel Press.
- Elgammal, A., Liu, B., Elhoseiny, M., and Mazzone, M. 2017. CAN: Creative Adversarial Networks, Generating Art by Learning About Styles and Deviating from Style Norms. In Proceedings of the 8th International Conference on Computational Creativity.
- Reimers, N. and Gurevych, I. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 3982-3992.
Index Terms
Keywords