1
In LLM Reasoning, there is Irrationality on top of Value Misalignment
即使对齐训练完美，大模型推理仍会偏离目标价值，文中用数学形式化定义了这一风险缺口。
arXiv:2606.20624v1 Announce Type: new Abstract: Significant progress has been made in aligning LLMs with target value functions. We argue that, even w…