Haoyu Feng

Navigating the Pareto Frontier of Alignment:Spectrum-Adaptive Fine-Tuning for LLMs

Supervised Fine-Tuning (SFT) with Negative Log-Likelihood (NLL) remains the standard post-training paradigm for Large Language Models, yet it imposes an excessive penalty on low-probability target tokens. This focus forces the model to prioritize minimizing the loss of difficult samples over optimiz…