A Lightweight and Scalable Conversational AI Framework for Intelligent Employee Onboarding
Source abstract
Abstract
Employee onboarding is a key process in workforce integration but is manual, time-consuming, and departmental. This paper presents OnboardGPT v1.0, an intelligent, scalable conversational AI platform to meet this task with automated and personalized onboarding experience through lightweight neural components. The platform uses a feedforward intent classification model, dense semantic retrieval through cosine similarity, and personalization aware of user profiles to deliver context-sensitive and relevant output. A 500-question proprietary dataset about onboarding and annotated answers was constructed to simulate real enterprise conversations from various roles and departments. The platform was launched with a Flask-based web interface that was not third-party API-dependent and enabled multi-turn dialogue, knowledge base searching, and role-aware task instruction. Experimental evaluation on performance indicators such as task success rate, intent classification accuracy, BLEU score, and user satisfaction in simulation demonstrates the system to be effective in offering coherent and actionable onboarding support. The contribution of this work includes a modular, explainable, and deployable AI pipeline suitable for onboarding automation at the enterprise level and lays the foundation for future extensions that include multilingual support, inclusion of long-term memory, and backend system interoperability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in Service Interactions · Explainable Artificial Intelligence (XAI) · Personal Information Management and User Behavior
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Bowen University, Iwo PMB 284, Osun State, Nigeria
School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban 4000, South Africa
Center for Applied Data Science, Faculty of Natural and Applied Sciences, Sol Plaatjee University, Kimberly 8301, South Africa
Department of Law, Bowen University, Iwo PMB 284, Osun State, Nigeria
Funding
Serestina Viriri
References (30)
Show source-provided references
1. The Effects of Onboarding on Organizational Life
2. Digital onboarding and employee outcomes: Empirical evidence from the UK10.1108/MD-11-2021-1528 ↗
3. Socialization resources theory and newcomers’ work engagement: A new pathway to newcomer socialization10.1108/CDI-12-2016-0214 ↗
4. AI-Augmented Learning and Development Platforms: Transforming Employee Training and Skill Enhancement
5. The ethics of people analytics: Risks, opportunities and recommendations
6. Frögéli, E., Jenner, B., and Gustavsson, P. (2023). Effectiveness of formal onboarding for facilitating organizational socialization: A systematic review. PLoS ONE, 18.10.1371/journal.pone.0281823 ↗
7. Chatbots and the new world of HCI10.1145/3085558 ↗
8. Application of deep belief networks for natural language understanding10.1109/TASLP.2014.2303296 ↗
9. Guo, Z., Yan, M., Qi, J., Zhou, J., He, Z., Lin, Z., and Wang, X. (2023). Few-shot table-to-text generation with prompt planning and knowledge memorization. arXiv.
10. Automated and secure onboarding for system of systems10.1109/ACCESS.2021.3102280 ↗
11. Zhang, Y., Sun, S., Galley, M., Chen, Y., Brockett, C., Gao, X., and Dolan, B. (2019). Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv.10.18653/v1/2020.acl-demos.30 ↗
12. Bauer, T. (2010). Maximizing Success, Society for Human Resource Management. Available online: www.shrm.org/foundation.
13. Artificial intelligence in human resources management: Challenges and a path forward10.1177/0008125619867910 ↗
14. Conversational agents in organisations: Strategic applications and implementation considerations10.4018/JGIM.20211101.oa53 ↗
15. Nimmagadda, S., Surapaneni, K., and Potluri, R. (2024). Artificial intelligence in HR: Employee engagement using Chatbots. Artificial Intelligence Enabled Management: An Emerging Economy Perspective, De Gruyter.10.1515/9783111172408-010 ↗
16. Brown, A., Davis, N., Miller, O., Wilson, E., Smith, L., and Lopez, S. (2024). Deep Learning Techniques for Enhancing Employee Turnover Prediction Accuracy, University of Califonia.
17. Singh, M., Srivastava, S., Srivastava, S., and Singhal, T. (2023, January 7–8). Unlocking Predictive Insights for Employee Retention and Engagement: Harnessing Machine Learning and Big Data Analytics in HR Practices. Proceedings of the International Conference on Mechanical and Energy Technologies, Greater Noida, India.10.1007/978-981-97-2716-2_44 ↗
18. AI-Driven Employee Engagement: Transforming HR Strategies for the Digital Workforce
19. Khamis, R. (2024). AI-Powered Learning Experience Platforms: Investigating Personalized Learning in the Workplace—A Case of an International Company in Sweden. [Master’s Thesis, University of Gothenburg].
20. Tariq, Z. (2024). Enhancing Onboarding with AI: Designing a Modern Conversational Agent for Onboarding. [Master’s Thesis, Lahti University of Technology LUT].
21. Boyer, J. (2023). Supporting and Educating New Employees with Onboarding: A Framework. [Ph.D. Thesis, Wilmington University].
22. Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv.
23. Retrieval-augmented generation for knowledge-intensive nlp tasks
24. Izacard, G., and Grave, E. (2020). Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. arXiv.10.18653/v1/2021.eacl-main.74 ↗
25. Wehnert, S., Sudhi, V., Dureja, S., Kutty, L., Shahania, S., and De Luca, E.W. (2021, January 21–25). Legal norm retrieval with variations of the bert model combined with tf-idf vectorization. Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law, New York, NY, USA.10.1145/3462757.3466104 ↗
26. Yogish, D., Manjunath, T., and Hegadi, R.S. (2019). Review on natural language processing trends and techniques using NLTK. Recent Trends in Image Processing and Pattern Recognition: Second International Conference, RTIP2R 2018, Solapur, India, 21–22 December 2018, Springer. Revised Selected Papers, Part III 2.10.1007/978-981-13-9187-3_53 ↗
27. Qu, C., Yang, L., Croft, W.B., Zhang, Y., Trippas, J.R., and Qiu, M. (2019, January 10–14). User intent prediction in information-seeking conversations. Proceedings of the 2019 Conference on Human Information Interaction and Retrieval, New York, NY, USA.10.1145/3295750.3298924 ↗
28. Ma, K., Cheng, H., Liu, X., Nyberg, E., and Gao, J. (2022). Open-domain question answering via chain of reasoning over heterogeneous knowledge. arXiv.10.18653/v1/2022.findings-emnlp.392 ↗
29. Datta, G., Joshi, N., and Gupta, K. (2022, January 14–16). Analysis of automatic evaluation metric on low-resourced language: BERTScore vs BLEU score. Proceedings of the International Conference on Speech and Computer, Gurugram, India.10.1007/978-3-031-20980-2_14 ↗
30. Mortezapour, S., Yamaguchi, S., and Ahmadon, M. (2025). A Deep Learning Model Based on Bidirectional Temporal Convolutional Network (Bi-TCN) for Predicting Employee Attrition. Appl. Sci., 15.10.3390/app15062984 ↗