Authors:
Sricharani P.,D. N. S. B. Kavitha,DOI NO:
https://doi.org/10.26782/jmcms.2026.04.00012Keywords:
Multimodal Learning,Large Language Models,Uncertainty Estimation,Career Assessment,Mock Interviews,Deep Learning,ATS Scoring,Abstract
Career Quest is an AI-enabled career assistance platform designed to enhance resume building and interview preparation through the integration of large language models (LLMs) and multimodal analytics. The system processes resumes using automated workflows and evaluates them using GPT-based models to generate ATS scores, semantic feedback, and job recommendations. For interview preparation, the platform incorporates multi-modal inputs, including text, speech, and facial expressions. Responses are analyzed using speech recognition, linguistic evaluation, and emotion detection models to assess technical accuracy, communication clarity, and behavioral traits. To improve reliability, the proposed framework introduces uncertainty estimation at each processing stage, enabling confidence-aware predictions rather than deterministic outputs. Additionally, a probabilistic fusion mechanism is incorporated to combine multi-modal signals, ensuring consistency across modalities. Experimental evaluation demonstrates strong performance in emotion detection (97.35%), speech hesitation detection (85%), and response evaluation. The system provides interpretable feedback along with reliability scores, making it a saleable and robust solution for career assessment and interview training.Refference:
I. Chou, Y.-C., Wongso, F. R., Chao, C.-Y., and Yu, H.-Y. “An AI Mock-Interview Platform for Interview Performance Analysis.” Proceedings of the 10th International Conference on Information and Education Technology (ICIET), 2022, pp. 37–41.
II. Harwell, Drew. “A Face-Scanning Algorithm Increasingly Decides Whether You Deserve the Job.” The Washington Post, 6 Nov. 2019.
III. HireVue. “Frequently Asked Questions.” HireVue, n.d.
IV. J. M. C. J., Sabi, M., Benson, M., Baburaj, G., and S. S. “Q&AI: An AI-Powered Mock Interview Bot for Enhancing the Performance of Aspiring Professionals.” Proceedings of the International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), 2024, pp. 1–5.
V. Pandey, R., Chaudhari, D., Bhawani, S., Pawar, O., and Barve, S. “Interview Bot with Automatic Question Generation and Answer Evaluation.” Proceedings of the 9th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE, 2023, pp. 1279–1286.
VI. Sricharani, P., Srikrishna, A., Kalyani, K., et al. “Intuitive Model Development and Data Preprocessing with Web and Command-Line Interfaces.” Grenze Journal of Engineering and Technology, vol. 10, no. 2, June 2024, pp. 3330–3338.
VII. Uriawan, W., Widodo, R. I. H., Ramadita, R., Herdiyanto, R. F., Marsaputra, R. S., and Nurrobianti, S. “Implementing Large Language Model API for Interview Training Based on Job Description.” Preprints, July 2024.