Akhil Reddy Bairi, et al. “Unified Pipelines for Multi-Dimensional LLM Optimization Through SFT, RLHF, and DPO”. Journal of AI-Assisted Scientific Discovery, vol. 4, no. 2, Sept. 2024, pp. 325-66, https://scienceacadpress.com/index.php/jaasd/article/view/285.