1
Some Large Language Models Exhibit Consistent Risk Attitudes
最新研究揭示：部分大语言模型在风险决策中展现出与人类一致且稳定的风险态度，这对AI安全与行为对齐很有启发。
arXiv:2607.16197v1 Announce Type: new Abstract: As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimens…