Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
大模型会听指令还是学案例?论文揭示LLMs在指令服从与上下文归纳之间的行为冲突,揭秘“说一套做一套”的根源。
arXiv:2605.20382v1 Announce Type: new Abstract: Language models are trained to follow instructions, but they are also powerful pattern completers. Wha…