连续世界中的离散心智：语言模型知道时间在流逝吗？
Discrete Minds in a Continuous World: Do Language Models Know Time Passes?
AI总结：
本文通过对话时长判断、紧急问答和BombRush导航三项实验，检验LLM能否感知真实时间流逝并据此调整决策。
摘要：
尽管大型语言模型（LLM）擅长事件排序和持续时间估计等时间推理任务，但它们感知真实时间流逝的能力仍未得到探索。我们通过三个互补实验考察LLM是否能感知时间流逝并据此调整决策。首先，我们提出Token-Time Hypothesis（令牌-时间假说），认为LLM能够将离散的令牌数量映射到连续的实际时间，并通过对话时长判断任务对此进行验证。其次，我们证明在问答任务中，当用户表达紧迫感时，LLM可以利用这种意识调整回答长度，同时保持准确性。最后，我们开发了BombRush，这是一种交互式导航挑战，用于检验LLM在动态环境中、不断增强的时间压力下如何改变行为。研究结果表明，LLM具有一定的时间流逝意识，能够在离散语言令牌与连续物理时间之间建立联系，尽管这种能力会随模型规模和推理能力而变化。本工作为在时间敏感型应用中增强LLM的时间意识奠定了理论基础。
英文摘要：
While Large Language Models (LLMs) excel at temporal reasoning tasks like event ordering and duration estimation, their ability to perceive the actual passage of time remains unexplored. We investigate whether LLMs perceive the passage of time and adapt their decision-making accordingly through three complementary experiments. First, we introduce the Token-Time Hypothesis, positing that LLMs can map discrete token counts to continuous wall-clock time, and validate this through a dialogue duration judgment task. Second, we demonstrate that LLMs could use this awareness to adapt their response length while maintaining accuracy when users express urgency in question answering tasks. Finally, we develop BombRush, an interactive navigation challenge that examines how LLMs modify behavior under progressive time pressure in dynamic environments. Our findings indicate that LLMs possess certain awareness of time passage, enabling them to bridge discrete linguistic tokens and continuous physical time, though this capability varies with model size and reasoning abilities. This work establishes a theoretical foundation for enhancing temporal awareness in LLMs for time-sensitive applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
