使用迷宫测试评估大型语言模型中与意识相关的行为
Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test
AI总结：
本文通过迷宫测试评估12个大型语言模型的意识相关行为，发现推理型模型表现更优，但仍缺乏持续连贯的自我模型，说明其尚未具备真正的意识特征。
摘要：
我们使用迷宫测试研究大型语言模型（LLMs）中类似意识的行为，要求模型以第一人称视角在迷宫中导航。该测试同时考察空间感知、视角采择、目标导向行为和时间顺序组织——这些是与意识相关的关键特征。在将意识理论综合为13项基本特征后，我们在零样本、单样本和少样本学习场景下评估了12个领先的LLMs。结果显示，具备推理能力的LLMs持续优于标准版本，其中Gemini 2.0 Pro实现了52.9%的完整路径准确率，DeepSeek-R1达到了80.5%的部分路径准确率。这两项指标之间的差距表明，LLMs难以在整个求解过程中维持连贯的自我模型——这是意识的一个基本方面。尽管LLMs通过推理机制在与意识相关的行为上取得了进展，但它们缺乏意识所特有的整合性、持续性的自我觉知。
英文摘要：
We investigate consciousness-like behaviors in Large Language Models (LLMs) using the Maze Test, challenging models to navigate mazes from a first-person perspective. This test simultaneously probes spatial awareness, perspective-taking, goal-directed behavior, and temporal sequencing-key consciousness-associated characteristics. After synthesizing consciousness theories into 13 essential characteristics, we evaluated 12 leading LLMs across zero-shot, one-shot, and few-shot learning scenarios. Results showed reasoning-capable LLMs consistently outperforming standard versions, with Gemini 2.0 Pro achieving 52.9% Complete Path Accuracy and DeepSeek-R1 reaching 80.5% Partial Path Accuracy. The gap between these metrics indicates LLMs struggle to maintain coherent self-models throughout solutions -- a fundamental consciousness aspect. While LLMs show progress in consciousness-related behaviors through reasoning mechanisms, they lack the integrated, persistent self-awareness characteristic of consciousness.
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。
