监督微调需要解锁标记优先的潜力
Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
AI总结：
本文提出标记优先作为监督微调的关键桥梁，通过分布重塑过程实现数据与理想对齐流形的匹配，并分析了噪声过滤和有毒模式卸载两种不同的研究领域。
摘要：
从拟合经验数据到实现真正的人类效用的转变本质上受到粒度不匹配的限制，其中细粒度自回归生成往往由粗略或均匀的信号进行监督。本文主张标记优先作为关键桥梁，将监督微调（SFT）不视为简单的优化，而是作为精确分布重塑过程，使原始数据与理想对齐流形对齐。我们通过这一统一视角分析最近的突破，将其分为两个不同的领域：正优先用于噪声过滤和带符号优先用于有毒模式卸载。我们回顾了现有进展和局限性，识别了关键挑战，并提出了未来研究的方向。
英文摘要：
The transition from fitting empirical data to achieving true human utility is fundamentally constrained by a granularity mismatch, where fine-grained autoregressive generation is often supervised by coarse or uniform signals. This position paper advocates Token Priority as the essential bridge, formalizing Supervised Fine-Tuning (SFT) not as simple optimization but as a precise distribution reshaping process that aligns raw data with the ideal alignment manifold. We analyze recent breakthroughs through this unified lens, categorizing them into two distinct regimes: Positive Priority for noise filtration and Signed Priority for toxic modes unlearning. We revisit existing progress and limitations, identify key challenges, and suggest directions for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
