LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate this distinction using the St. Petersburg game as a controlled testbed, a classical paradox in which the expected payoff is infinite, yet humans typically report low, finite willingness to pay. We evaluate 28 LLMs with a structured prompt suite that includes the original game; controlled decision variants that perturb truncation, repeated play, numeric endowment, and occupational identity; a human-perspective prompt that asks models to reason as human decision makers; and paired comparisons between base models and their instruction-tuned counterparts. In the original game, most models generate finite bids, creating the appearance of human-like risk behavior. However, this outcome-level resemblance masks substantial mechanism-level differences. The controlled variants reveal that rather than maintaining human-like behavior seen in the original game, models often shift to conditionally and computationally rational behavior. Human-cue prompting and instruction tuning often lower bids and reduce some visible pathologies, but most mechanism-level response patterns remain largely unchanged. These findings show that behavioral alignment in risk decision-making can be surface-level: LLMs may produce human-like risk decisions without exhibiting human-consistent mechanisms. High-stakes evaluations of LLM decision-making should therefore move beyond outcome similarity and examine whether the alignment is supported by mechanism-level consistency.

翻译：大语言模型在风险决策任务中可能表现出谨慎态度，但看似谨慎的输出并不必然表明其与人类决策机制一致。我们以圣彼得堡博弈为受控实验平台，这一经典悖论中预期收益无限，但人类通常报出较低且有限的支付意愿。我们评估了28个LLM，采用包含以下结构的提示套件：原始博弈；通过扰动截断参数、重复博弈次数、数字资产及职业身份形成的受控决策变体；要求模型以人类决策者身份进行推理的人类视角提示；以及基座模型与其指令微调版本的配对比较。在原始博弈中，大多数模型生成有限报价，呈现出类似人类风险行为的表象。然而，这种结果层面的相似性掩盖了深层的机制差异。受控变体显示，模型在原始博弈中未保持人类典型行为，而是转向条件性计算理性行为。人类线索提示与指令微调通常降低报价并减少部分显性异常，但大多数机制层面的响应模式仍基本保持不变。这些发现表明，风险决策中的行为对齐可能仅停留在表层：LLM能产生类人风险决策，却未展现与人类一致的决策机制。因此，对LLM决策的高风险评估应超越结果相似性，审视对齐是否具备机制层面的一致性支撑。