Scholarly and Creative Works
2026
- Duarte-Vasquez, A., Thapa, B., Hooshmand, S., & Rathore, H. (2026). Training Ethical Language Models via Reinforcement Learning from AI Feedback.
2025
- Thapa, B., & Rathore, H. (n.d.). Topic Modeling Analysis of Ethical Framework Separability in LLM-Generated Moral Justifications.