AKHIL REDDY BAIRI; JAWAHARBABU JEYARAMAN; DEBABRATA DAS. Unified Pipelines for Multi-Dimensional LLM Optimization Through SFT, RLHF, and DPO. Journal of AI-Assisted Scientific Discovery, Riverside, USA, v. 4, n. 2, p. 325–366, 2024. Disponível em: https://scienceacadpress.com/index.php/jaasd/article/view/285.. Acesso em: 17 jan. 2025.