Akhil Reddy Bairi, Jawaharbabu Jeyaraman, and Debabrata Das. “Unified Pipelines for Multi-Dimensional LLM Optimization Through SFT, RLHF, and DPO”. Journal of AI-Assisted Scientific Discovery 4, no. 2 (September 18, 2024): 325–366. Accessed January 17, 2025. https://scienceacadpress.com/index.php/jaasd/article/view/285.