Download PDF

Structured Prompt Engineering for Auditing AI-Powered Hiring Tasks

Loubna Aminou, Abdelaziz Daaf, Maha Soulami, and Mohamed Youssfi
Computer Science, Artificial Intelligence and Cyber Security Lab, ENSET of Mohammedia, Hassan II University of Casablanca - Morocco.
How to cite: Loubna Aminou, Abdelaziz Daaf, Maha Soulami, and Mohamed Youssfi, "Structured Prompt Engineering for Auditing AI-Powered Hiring Tasks", Sciences Methods and Technologies International Journal (SciMeTech), (2026) Vol 2, Issue 2, p 77-83
Abstract
As part of their workflows, companies are incorporating Large Language Models for screening resumes and evaluating applicants. Nevertheless, prompt engineering biases and efficacy considerations are often ignored. This paper offers a baseline and evaluates the difference between the use of consistent, chain of thought prompting to evaluate candidates for a specialized blockchain node setup. With controlled experimentation of 15 candidates using Llama 3, the two prompt categories are analyzed for multiple metrics, including length, occurrence of domain-specific terms, and reasoning. Compared to baseline prompting, chain-of-thought prompting emerges as the preferred evaluative component for LLMs in hiring, replacing a less selective, black-box rating process with one that is more transparent, controllable, and accountable. We demonstrate how structured prompt design, using techniques like Chain-of-Thought, can enforce transparency and mitigate common failures. Our call-to-action targets design for prompt engineering as a first-class challenge in the development of AI hiring agents.
Keywords: Prompt engineering, AI hiring, Chain-of-Thought, Bias auditing, Large Language Models, Recruitment

References

  1. Zhang, Z., & Nasraoui, O. (2006, May). Mining search engine query logs for query recommendation. In Proceedings of the 15th international conference on World Wide Web (pp. 1039-1040).
  2. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877-1901.
  3. Lyu, Q., Havaldar, S., Stein, A., Zhang, L., Rao, D., Wong, E., ... & Callison-Burch, C. (2023, November). Faithful chain-of-thought reasoning. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 305-329).
  4. Gan, C., & Mori, T. (2023, June). A few-shot approach to resume information extraction via prompts. In International Conference on Applications of Natural Language to Information Systems (pp. 445-455). Cham: Springer Nature Switzerland.
  5. Reynolds, L., & McDonell, K. (2021, May). Prompt programming for large language models: Beyond the few-shot paradigm. In Extended abstracts of the 2021 CHI conference on human factors in computing systems (pp. 1-7).
  6. Mouraz, C., & Silva, J. M. Prompt quality assessment methods for rehabilitation projects: a contribution for the state-of-the-art. Proceedings of STARTCON.
  7. Schoenherr, J. R. (2022). Ethical artificial intelligence from popular to cognitive science: trust in the age of entanglement. Routledge.
  8. Lester, B., Al-Rfou, R., & Constant, N. (2021, November). The power of scale for parameter-efficient prompt tuning. In Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 3045-3059).
  9. Barocas, S., & Selbst, A. D. (2016). Big data's disparate impact. Calif. L. Rev., 104, 671.
  10. Dawson, J. Y., & Agbozo, E. (2024). AI in talent management in the digital era-an overview. Journal of Science and Technology Policy Management.
  11. Raghavan, M., Barocas, S., Kleinberg, J., & Levy, K. (2020, January). Mitigating bias in algorithmic hiring: Evaluating claims and practices. In Proceedings of the 2020 conference on fairness, accountability, and transparency (pp. 469-481).
  12. Chen, B., Zhang, Z., Langrene, N., & Zhu, S. (2025). Unleashing the potential of prompt engineering for large language models. Patterns, 6(6).
  13. Marvin, G., Hellen, N., Jingo, D., & Nakatumba-Nabende, J. (2023, June). Prompt engineering in large language models. In International conference on data intelligence and cognitive informatics (pp. 387-402). Singapore: Springer Nature Singapore.
  14. Ye, Q., Ahmed, M., Pryzant, R., & Khani, F. (2024, August). Prompt engineering a prompt engineer. In Findings of the Association for Computational Linguistics: ACL 2024 (pp. 355-385).
  15. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & 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.
  16. Lyu, K., Zhao, H., Gu, X., Yu, D., Goyal, A., & Arora, S. (2024). Keeping llms aligned after fine-tuning: The crucial role of prompt templates. Advances in Neural Information Processing Systems, 37, 118603-118631.
  17. Peng, J., Yang, W., Wei, F., & He, L. (2024). Prompt for extraction: Multiple templates choice model for event extraction. Knowledge-based systems, 289, 111544.
  18. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., ... & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35, 24824-24837.
  19. Kadam, S., & Vaidya, V. (2018, December). Review and analysis of zero, one and few shot learning approaches. In International Conference on Intelligent Systems Design and Applications (pp. 100-112). Cham: Springer International Publishing.
  20. Habib, A., Abdulmahmod, O. F., Raza, M., Gu, Y. H., Aydogan, M., & Al-antari, M. A. (2025, September). Towards Explainable AI in Agentic Retrieval-Augmented Generation: A Systematic Review. In 2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP) (pp. 1-8). IEEE.
  21. Debenedetti, E., Shumailov, I., Fan, T., Hayes, J., Carlini, N., Fabian, D., & Tramer, F. (2025). Defeating prompt injections by design. arXiv preprint arXiv:2503.18813.
  22. Kordzadeh, N., & Ghasemaghaei, M. (2022). Algorithmic bias: review, synthesis, and future research directions. European Journal of Information Systems, 31(3), 388-409.
  23. Sato, K., Kaneko, H., & Fujimura, M. (2024). Reducing cultural hallucination in non-english languages via prompt engineering for large language models. OSF Preprints, 10, 1-8.
  24. Bura, C., Myakala, P. K., & Jonnalgadda, A. K. (2025). Ethical prompt engineering: addressing bias, transparency, and fairness. Int J Res Anal Rev (IJRAR), 12(1).
SciMeTech กค Vol 2, Issue 2 กค p 77-83