揭示大型语言模型中的心智理论：与人类大脑中单个神经元的平行比较
Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain
AI总结：
本研究借鉴人类大脑中dmPFC神经元支撑心智理论的机制，发现大型语言模型的隐藏嵌入能对真假信念试验产生响应，其活动与任务表现相关且依赖模型规模，并能群体解码他人信念，揭示了LLMs与人类神经元在心智理论上的平行性。
摘要：
随着大型语言模型（LLMs）的近期发展，人们发现它们表现出一定水平的心智理论（ToM），这是一种复杂的认知能力，与我们的意识心智相关，使我们能够推断他人的信念和观点。虽然人类的心智理论能力被认为源自广泛互联的大脑网络（包括背内侧前额叶皮层（dmPFC）神经元）的神经活动，但LLMs具备心智理论能力的具体过程或它们与人类心智理论能力的相似性在很大程度上仍然未知。在本研究中，我们从支撑人类心智理论的dmPFC神经元中汲取灵感，并采用类似的方法来检验LLMs是否表现出可比的特征。令人惊讶的是，我们的分析揭示了二者之间惊人的相似性，因为LLMs内部的隐藏嵌入（人工神经元）开始对真信念或假信念试验表现出显著的响应性，这表明它们能够表征他人的视角。这些人工嵌入响应与LLMs在心智理论任务中的表现密切相关，这一特性依赖于模型的大小。此外，利用整个嵌入可以准确解码他人的信念，表明嵌入在心智理论能力上存在群体层面的表现。总之，我们的研究结果揭示了LLMs嵌入的一种涌现特性，即其活动随心智理论特征而调整，为人工模型与人类大脑神经元之间的平行性提供了初步证据。
英文摘要：
With their recent development, large language models (LLMs) have been found to exhibit a certain level of Theory of Mind (ToM), a complex cognitive capacity that is related to our conscious mind and that allows us to infer another's beliefs and perspective. While human ToM capabilities are believed to derive from the neural activity of a broadly interconnected brain network, including that of dorsal medial prefrontal cortex (dmPFC) neurons, the precise processes underlying LLM's capacity for ToM or their similarities with that of humans remains largely unknown. In this study, we drew inspiration from the dmPFC neurons subserving human ToM and employed a similar methodology to examine whether LLMs exhibit comparable characteristics. Surprisingly, our analysis revealed a striking resemblance between the two, as hidden embeddings (artificial neurons) within LLMs started to exhibit significant responsiveness to either true- or false-belief trials, suggesting their ability to represent another's perspective. These artificial embedding responses were closely correlated with the LLMs' performance during the ToM tasks, a property that was dependent on the size of the models. Further, the other's beliefs could be accurately decoded using the entire embeddings, indicating the presence of the embeddings' ToM capability at the population level. Together, our findings revealed an emergent property of LLMs' embeddings that modified their activities in response to ToM features, offering initial evidence of a parallel between the artificial model and neurons in the human brain.
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。
