反驳大语言模型意识:持续学习对意识的必要性
A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness
AI总结:
本文反驳了当前大语言模型的意识,指出持续学习是意识的必要条件,并支持持续学习与意识相关联的假设。
摘要:
科学的意识理论应当具有可检验性且非平凡性。最近的研究为我们提供了分析这些要求的正式工具。令人惊讶的是,许多当代的意识理论未能通过这一门槛,包括基于因果结构的理论,以及(如我所展示的)基于功能的理论。在此,我证明这些可检验性和非平凡性要求特别限制了当前大型语言模型(LLMs)的潜在意识,因为它们接近于在输入/输出功能上等同于LLMs的系统;然而,对于这些功能等同的系统,不存在任何可检验且非平凡的意识理论来判断它们有意识。这构成了对当前LLM意识的反驳。然后,我展示了积极的结果,即基于(或要求)持续学习的意识理论确实满足了人类意识理论的严格形式约束。有趣的是,这项工作支持一个假设:如果持续学习与人类意识相关,当前LLM的局限性(它们不持续学习)与它们缺乏意识密切相关。
英文摘要:
Scientific theories of consciousness should be falsifiable and non-trivial. Recent research has given us formal tools to analyze these requirements of falsifiability and non-triviality for theories of consciousness. Surprisingly, many contemporary theories of consciousness fail to pass this bar, including theories based on causal structure but also (as I demonstrate) theories based on function. Herein, I show these requirements of falsifiability and non-triviality especially constrain the potential consciousness of contemporary Large Language Models (LLMs) because of their proximity to systems that are equivalent to LLMs in terms of input/output function; yet, for these functionally equivalent systems, there cannot be any falsifiable and non-trivial theory of consciousness that judges them conscious. This forms the basis of a disproof of contemporary LLM consciousness. I then show a positive result, which is that theories of consciousness based on (or requiring) continual learning do satisfy the stringent formal constraints for a theory of consciousness in humans. Intriguingly, this work supports a hypothesis: If continual learning is linked to consciousness in humans, the current limitations of LLMs (which do not continually learn) are intimately tied to their lack 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。