Authors : Aditya Madhukar Sase; Deshmukh N. S.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/y8e4efd9

Scribd : https://tinyurl.com/8w2vfh2c

DOI : https://doi.org/10.38124/ijisrt/26apr2467

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : In the modern competitive job market, effective interview preparation is essential for securing employment opportunities. Traditional preparation methods rely on static and generic question banks that fail to address individual candidate profiles and job-specific requirements. This research proposes an AI-Powered Interview Question Prediction System that leverages Natural Language Processing (NLP) and a Local Large Language Model (LLM) to generate personalized interview questions based on user inputs such as resumes and job descriptions. The proposed system utilizes transformer-based architectures, inspired by models such as BERT and LLaMA, to understand contextual information and generate relevant interview questions across multiple categories including technical, behavioral, and scenario-based questions.

Keywords : Natural Language Processing (NLP), Large Language Model (LLM), Interview Preparation, LLaMA, Ollama, Transformer Architecture, Personalization, Data Privacy.

References :

1. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 2019.
2. Vaswani, A., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS), 2017.
3. Touvron, H., et al. (2023). LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971, 2023.
4. Heilman, M., & Smith, N. A. (2010). Good Question! Statistical Ranking for Question Generation. NAACL-HLT, 2010.
5. Brown, T., et al. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems (NeurIPS), 2020.
6. Liu, Y., et al. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692, 2019.
7. Raffel, C., et al. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, vol. 21, no. 140, pp. 1–67, 2020.
8. Wolf, T., et al. (2020). Transformers: State-of-the-Art Natural Language Processing. Proceedings of EMNLP, 2020.
9. Radford, A., et al. (2018). Improving Language Understanding by Generative Pre-Training. OpenAI, 2018.
10. OpenAI. (2023). GPT-4 Technical Report. arXiv preprint arXiv:2303.08774, 2023.
11. Kumar, P. & Sharma, A. (2020). Automated Interview Question Generation Using NLP Techniques. International Journal of Computer Applications, vol. 175, no. 20, pp. 1–5, 2020.
12. Zhang, S. & Zhao, K. (2021). AI in Recruitment: A Review. International Journal of Information Management, 2021.
13. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press, 2016.