大模型最值钱的能力，恰恰是无法用规则解释的部分。
Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones
- 用反证法证明：若能用人类规则完全描述，就等于专家系统，但专家系统弱于大模型。
- 历史事实表明专家系统能力受限，而大模型超越了规则体系的边界。
- 适合关注AI可解释性、安全性和认知局限的研究者阅读。
本文提出并论证一个反直觉观点：大型语言模型（LLMs）真正有价值的能力，恰恰存在于无法被人类可读的离散规则所完整捕捉的部分。核心论点通过专家系统等价性进行反证：若大模型的所有能力都能由一套完整的可读规则描述，则该规则集在功能上等同于专家系统；但历史与实证已表明，专家系统严格弱于大模型；由此产生矛盾——大模型超出专家系统的能力，正是无法被规则编码的部分。该观点进一步得到中国哲学中‘悟’（突然通过实践获得洞察）的概念、专家系统的历史失败，以及人类认知工具与复杂系统之间结构性不匹配的支持。论文探讨了其对可解释性研究、人工智能安全和科学认识论的影响。
原文摘要 · Abstract (English)
This paper proposes and argues for a counterintuitive thesis: the truly valuable capabilities of large language models (LLMs) reside precisely in the part that cannot be fully captured by human-readable discrete rules. The core argument is a proof by contradiction via expert system equivalence: if the full capabilities of an LLM could be described by a complete set of human-readable rules, then that rule set would be functionally equivalent to an expert system; but expert systems have been historically and empirically demonstrated to be strictly weaker than LLMs; therefore, a contradiction arises -- the capabilities of LLMs that exceed those of expert systems are exactly the capabilities that cannot be rule-encoded. This thesis is further supported by the Chinese philosophical concept of Wu (sudden insight through practice), the historical failure of expert systems, and a structural mismatch between human cognitive tools and complex systems. The paper discusses implications for interpretability research, AI safety, and scientific epistemology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。