From Error to Insight: Pedagogical Reflections on AI Hallucinations and Prompt Engineering
Abstract
This paper investigates the interplay between prompt engineering and artificial intelligence (AI) hallucinations in the university context, not merely as technological phenomena but as reflections of human learning, reasoning, and truth-seeking in the digital era. The study aims to examine how carefully designed prompts can enhance the reliability of AI-generated outputs while transforming hallucinations—commonly perceived as system failures—into opportunities for critical reflection and ethical development.
A qualitative-documentary methodology was employed, combining bibliometric mapping of 33 recent publications (2021–2025) with interpretive analysis. The findings indicate that prompt engineering constitutes a novel dimension of digital and critical literacy, enabling students to articulate ideas with clarity, intentionality, and responsibility. Conversely, AI hallucinations highlight the limitations of statistical reasoning and serve as reminders that information alone does not guarantee understanding.
From a pedagogical perspective, both phenomena underscore the importance of teaching AI literacy as a facet of human literacy—one that integrates creativity with discernment and efficiency with ethical responsibility. The study concludes that education must move “from error to insight,” leveraging technological uncertainty as moments for learning, reflection, and self-awareness. Ultimately, while artificial intelligence can support human cognition, it is the human capacity for ethical judgment, empathy, and reflective thinking that imbues every algorithmic output with meaning.
Keywords: Artificial Intelligence; Higher Education; Prompt Engineering; AI Literacy; Digital Literacy; Epistemology; Academic Ethics.
Full Text:
PDFReferences
S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed., Pearson, USA, 2021.
B. Marr, Artificial Intelligence in Practice, Wiley, UK, 2022.
OpenAI, GPT-4 Technical Report, 2023. [Online]. Available: https://cdn.openai.com/papers/gpt-4.pdf
European Commission, Ethics Guidelines for Trustworthy AI, Publications Office of the EU, 2021.
F. A. Batarseh and E. A. Latif, AI Assurance: Towards Trustworthy Artificial Intelligence, Elsevier, UAE, 2021.
A. Bozkurt, “Tell me your prompts and I will make them true: An OpenAI reflection on the art of prompt engineering,” Open Praxis, vol. 16, no. 2, pp. 661–677, 2023.
IBM, “What are AI hallucinations?” IBM Think, 2023. [Online]. Available: https://www.ibm.com/think/topics/ai-hallucinations
Y. Zhang, Y. Li, and L. Cui, “Siren’s song in the AI ocean: A survey on hallucination in large language models,” arXiv preprint, 2023. [Online]. Available: https://arxiv.org/abs/2309.01219
R. Hernández-Sampieri, C. Fernández-Collado, and P. Baptista, Research Methodology, 7th ed., McGraw-Hill, Mexico, 2022.
C. Lo et al., “The impact of prompt engineering and a generative AI-driven tool in university education,” Education Sciences, vol. 15, no. 2, p. 199, 2024.
A. Min et al., “Unleashing the potential of prompt engineering for large language models,” Patterns (Cell Press), vol. 6, no. 1, p. 100108, 2025.
H. Sarı et al., “Developing AI literacy through prompt engineering practices in higher education,” Computers and Education: Artificial Intelligence, vol. 7, p. 100222, 2024.
T. I. Tonmoy, S. M. M. Zaman, and V. Rawte, “A comprehensive survey of hallucination mitigation techniques in large language models,” arXiv preprint, 2024. [Online]. Available: https://arxiv.org/abs/2401.01313
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, USA, 2016.
P. Domingos, The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World, Basic Books, USA, 2015.
L. Weng, “Understanding and mitigating hallucination in large language models,” Towards Data Science, 2024. [Online]. Available: https://lilianweng.github.io/posts/2024-07-07-hallucination
J. Nouri, “AI ethics and responsibility in higher education: Preparing for human–AI collaboration,” Computers & Education, vol. 193, p. 104656, 2022.
M. Rahman, “Reducing hallucination rates in transformer-based models for education,” SpringerOpen Journal of AI Research and Applications, vol. 3, pp. 45–58, 2022.
M. Foucault, Power/Knowledge: Selected Interviews and Other Writings 1972–1977, Pantheon Books, New York, 1980.
R. Al-Jarf, “Digital literacy and the rise of prompt engineering in language education,” Education and Information Technologies, vol. 29, no. 2, pp. 453–469, 2023.
C. Lai and Y. He, “Prompt-driven learning and data-informed pedagogy: A new approach to digital education,” Learning Analytics (Elsevier), vol. 15, no. 1, pp. 1–12, 2024.
E. Crawley, J. Malmqvist, and D. Brodeur, Rethinking Engineering Education: The CDIO Approach, 3rd ed., Springer, Cham, 2023.
J. Aldana G., “CDIO-based innovation in higher education: Integrating AI, creativity, and reflective learning,” University of Quindío Research Reports, 2024.
H. Qiu et al., “Bias control and transparency in generative AI systems,” IEEE Access, vol. 11, pp. 22511–22523, 2023.
J. Cao, “Epistemology of artificial intelligence: From data to meaning,” AI & Society, vol. 39, no. 4, pp. 1050–1064, 2024.
M. Haque, “Evaluating the pedagogical potential of LLMs in engineering education,” IEEE Transactions on Education, vol. 67, no. 2, pp. 134–145, 2024.
P. Kaur, “Algorithmic transparency and human–machine accountability,” Informatics (MDPI), vol. 11, no. 3, p. 71, 2023.
J. Park and S. Lee, “Human–AI co-learning: Ethical challenges and opportunities,” AI Ethics (Springer), vol. 5, pp. 211–226, 2023.
A. Ghosh, “Multimodal prompting and interpretability in LLMs,” Applied Sciences (MDPI), vol. 13, no. 10, p. 5622, 2023.
M. Pereira, “Academic integrity and AI-assisted writing: Policy perspectives,” Education and Artificial Intelligence (Elsevier), vol. 2, no. 1, pp. 55–68, 2024.
W. Li and X. Zhou, “Prompt design strategies for adaptive learning environments,” SpringerOpen Journal of Intelligent Systems, vol. 12, no. 3, pp. 221–238, 2024.
D. Chien, “Prompt taxonomy and language model interpretability,” Information (MDPI), vol. 16, no. 1, p. 95, 2025.
A. Turing, The Philosophy of Machine Intelligence: Collected Essays, Oxford University Press, UK, 2022.
Refbacks
- There are currently no refbacks.
