Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities. We investigate this discrepancy and identify a fundamental distributional gap: while RL aligns with the model's internal belief, SFT forces the model to fit external supervision. This mismatch often manifests as "Confident Conflicts" tokens characterized by low probability but low entropy. In these instances, the model is highly confident in its own prediction but is forced to learn a divergent ground truth, triggering destructive gradient updates. To address this, we propose Entropy-Adaptive Fine-Tuning (EAFT). Unlike methods relying solely on prediction probability, EAFT utilizes token-level entropy as a gating mechanism to distinguish between epistemic uncertainty and knowledge conflict. This allows the model to learn from uncertain samples while suppressing gradients on conflicting data. Extensive experiments on Qwen and GLM series (ranging from 4B to 32B parameters) across mathematical, medical, and agentic domains confirm our hypothesis. EAFT consistently matches the downstream performance of standard SFT while significantly mitigating the degradation of general capabilities.

翻译：监督微调是领域适应的标准范式，但常导致灾难性遗忘。与之形成鲜明对比的是，策略强化学习能有效保留通用能力。我们探究这一差异并发现一个根本性的分布鸿沟：强化学习与模型内部信念保持一致，而监督微调迫使模型拟合外部监督。这种不匹配常表现为“置信冲突”标记，其特征是低概率但低熵值。在这些情况下，模型对其自身预测高度自信，却被强制学习相悖的真实标签，从而引发破坏性梯度更新。为解决此问题，我们提出熵自适应微调。与仅依赖预测概率的方法不同，EAFT利用标记级熵值作为门控机制来区分认知不确定性与知识冲突。这使得模型能够从不确定样本中学习，同时抑制冲突数据的梯度。在Qwen和GLM系列模型上进行的广泛实验证实了我们的假设。EAFT在数学、医疗和智能体领域均能保持与标准监督微调相当的下游性能，同时显著缓解通用能力的退化。