Abstract
Generative AIs have become widespread and are being used for various purposes. However, a phenomenon called hallucination, in which generative AI outputs plausible lies, is being viewed as a problem. While hallucination is a problem when it is important to be factual, in some cases, such as idea generation, it is not a problem. In fact, in some cases, it may be better to have hallucination occur to come up with surprising and diverse ideas. In this study, we compared several prompts with the aim of getting ChatGPT to output information that differs from the training data for GPT when generating ideas for a fictional historical novel. The results showed that it was more effective and led to generation of more surprising ideas to directly instruct ChatGPT to include content that differs from the facts within the prompt rather than using adversarial prompts that cause hallucinations.
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
Similar content being viewed by others
References
Athaluri, S.A., Manthena, S.V., Kesapragada, V.K.M., Yarlagadda, V., Dave, T., Duddumpudi, R.T.S.: Exploring the boundaries of reality: investigating the phenomenon of artificial intelligence hallucination in scientific writing through ChatGPT references. Cureus 15(4) (2023)
Girotra, K., Meincke, L., Terwiesch, C., Ulrich, K.T.: Ideas are dimes a dozen: Large language models for idea generation in innovation (2023). Available at SSRN 4526071
Li, J., Cheng, X., Zhao, X., Nie, J., Wen, J.: HaluEval: a large-scale hallucination evaluation benchmark for large language models. In: EMNLP 2023, pp. 6449–6464 (2023). https://doi.org/10.18653/v1/2023.emnlp-main.397
McKenna, N., Li, T., Cheng, L., Hosseini, M.J., Johnson, M., Steedman, M.: Sources of hallucination by large language models on inference tasks. In: EMNLP 2023, pp. 2758–2774 (2023). https://doi.org/10.18653/v1/2023.findings-emnlp.182
Pacchiardi, L., et al.: How to catch an AI liar: lie detection in black-box LLMs by asking unrelated questions. In: ICLR 2024 (2024). https://doi.org/10.48550/arXiv.2309.15840
Yao, J., Ning, K., Liu, Z., Ning, M., Yuan, L.: LLM lies: hallucinations are not bugs, but features as adversarial examples. CoRR abs/2310.01469 (2023). https://doi.org/10.48550/arXiv.2310.01469
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tachibana, M., Shimizu, T., Tomiura, Y. (2025). Generating Surprising and Diverse Ideas Using ChatGPT. In: Oliver, G., Frings-Hessami, V., Du, J.T., Tezuka, T. (eds) Sustainability and Empowerment in the Context of Digital Libraries. ICADL 2024. Lecture Notes in Computer Science, vol 15493. Springer, Singapore. https://doi.org/10.1007/978-981-96-0865-2_18
Download citation
DOI: https://doi.org/10.1007/978-981-96-0865-2_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-96-0864-5
Online ISBN: 978-981-96-0865-2
eBook Packages: Computer ScienceComputer Science (R0)