| Creator | Rhodes Evening High School - Greece |
| Description | The resource presents few-shot prompting: the technique of giving the machine two or three pre-solved examples before the real task in order to stabilise output and align it with the teacher's expectations. It explains how to choose and order exemplars and when zero-shot or one-shot is enough. The critical focus is that the stability of form does not guarantee the correctness of content. |
| Keywords | few-shot prompting; exemplars; output stability; zero-shot; one-shot; prompt engineering; in-context learning; verification |
| Affiliation | Rhodes Evening High School - Greece |
| Contributor | STIAEM Transnational Scientific Board (peer review, Rhodes validation protocol) |
| Media Format | Text; Infographics |
| Genre | Training Manual; Educational Guide |
| Educational Level | Secondary School |
| Module / Section | Module 4 - Prompt Engineering for Inclusive Education / Video 4.2 - Advanced Prompting and Chain-of-Thought |
| Learning Objectives | Explain what distinguishes few-shot prompting from a simple request of a task, and why it stabilises the output; build two or three mutually coherent worked examples and use them as a model for the new task; evaluate critically the limits of the technique, knowing that stability of form does not guarantee correctness of content. |
| Rights / License | Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| Date Available | 14/09/2026 |
| Citation | Rhodes Evening High School. (2026). Few-Shot Prompting Strategies: Using Pre-Solved Exemplar Models for Output Stability [Educational guide]. Slow Tech Innovation: AI, Ethics, and New Teaching Methods (STIAEM), 2025-1-IT02-KA220-SCH-000365213. |
| URL | https://www.stiaemproject.eu/?oer=OER-4.2.1 |
| References | 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., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. CAST. (2024). Universal Design for Learning Guidelines version 3.0. https://udlguidelines.cast.org/ Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022). Rethinking the role of demonstrations: What makes in-context learning work? In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (pp. 11048–11064). Association for Computational Linguistics. https://aclanthology.org/2022.emnlp-main.759/ Redecker, C. (2017). European framework for the digital competence of educators: DigCompEdu. Publications Office of the European Union. https://doi.org/10.2760/159770 Renkl, A. (2014). Toward an instructionally oriented theory of example-based learning. Cognitive Science, 38(1), 1–37. https://doi.org/10.1111/cogs.12086 Sweller, J., & Cooper, G. A. (1985). The use of worked examples as a substitute for problem solving in learning algebra. Cognition and Instruction, 2(1), 59–89. https://doi.org/10.1207/s1532690xci0201_3 UNESCO. (2023). Guidance for generative AI in education and research. UNESCO. |