本文旨在对意识的整合信息理论（Integrated Information Theory, IIT）进行全面的批判性评价，探究该理论的演进历程及涉及的问题。IIT是一种认为意识可通过整合信息加以解释的假说，主张体验的诸多基本属性可通过物理系统的信息属性得到恰当分析与解释。过去十年间，IIT在理论架构与数学模型方面取得了诸多进展。此外，与意识科学领域的所有假说一样，IIT也引发了若干争议与问题，在此背景下，迫切需要对IIT开展批判性综述。为此，本文首先介绍IIT的基本概念及相关问题，随后讨论IIT经历的主要转变并指出相关的模型内部问题，最后在末节提出IIT原理涉及的若干理论层面的模型外部问题。文章结论指出，为未来发展计，IIT应更严肃地对待体验的元认知可及性。
英文摘要：
The purpose of this article is to provide an overall critical appraisal of Integrated Information Theory(IIT) of consciousness. We explore how it has evolved and what problems are involved in the theory. IIT is a hypothesis that consciousness can be explained in terms of integrated information. It argues that a number of fundamental properties of experience can be properly analyzed and explained by physical systems' informational properties. Throughout the last decade, there have been many advances in IIT's theoretical structure and mathematical model. In addition, like all hypotheses in the field of science of consciousness, IIT has given rise to several controversies and issues. In this context, a critical survey for IIT is urgently needed. To this end, we first introduce fundamental concepts of IIT and related issues. Thereafter, we discuss major transitions IIT has been through and point out related intra-model issues. Finally, in the last section, some theoretical, extra-model issues involved in IIT's principles are presented. The article concludes by suggesting that, for the sake of future development, IIT should more seriously take metacognitive accessibility to experience.
Integrated information theory: the good, the bad and the misunderstood
University of Sussex（苏塞克斯大学）；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；Imperial College London（伦敦帝国理工学院）；University of Oxford（牛津大学）；Queen Mary University of London（伦敦大学玛丽女王学院）；Canadian Institute for Advanced Research（加拿大高级研究院）
Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis
Bridging integrated information theory and the free-energy principle in living neuronal networks
The University of Tokyo（东京大学）；International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo Institutes for Advanced Study (UTIAS)（东京大学高等研究院神经智能国际研究中心（WPI-IRCN））
Measuring Integrated Information: Comparison of Candidate Measures in Theory and Simulation
整合信息理论（Integrated Information Theory，IIT）是一种重要的意识理论，其核心措施是量化系统产生的信息超过其部分总和的程度。虽然几个候选措施的综合信息（“$Φ$”）现在存在，很少有人知道他们如何比较，特别是在他们的行为方面的非平凡的网络模型。在这篇文章中，我们提供了六个不同的候选措施的清晰和直观的描述。然后，我们探索这些措施的每一个属性在模拟网络上由八个相互作用的节点，动画与高斯线性自回归动力学。我们发现这些措施的行为有着惊人的多样性--没有两个措施在所有分析中表现出一致的一致性。此外，只有一个子集的措施似乎真正反映了某种形式的动态复杂性，在系统组件之间的同步隔离和集成的意义上。我们的研究结果有助于指导IIT的操作化，并推动可能具有更普遍适用性的综合信息措施的发展。
