语言让推理变得可计算，大模型验证了语言对思维的重塑作用
Language and Thought: The View from LLMs
- 用语言编码的抽象性提升跨领域推理效率
- 大模型虽有限但仍能实现广泛领域的推断能力
- 为语言如何塑造人类思维提供新证据
丹尼尔·丹内特在1996年的《心灵种类》中提出：给心智加入语言后，其性质可能与无语言心智截然不同，甚至不应同称为‘心智’。近期人工智能研究通过对比有无语言训练的系统表现，可视为对这一观点的实验检验。本文认为，大语言模型在推理任务上的成功——尽管能力有限——支持丹内特关于语言对思维具有根本性影响的激进观点。核心在于语言编码的抽象性与高效性，使模型能在多领域实现推断。简言之，语言使推理在计算上变得可行。这些发现也为理解语言在人类生物心智中的作用提供了新视角。
原文摘要 · Abstract (English)
Daniel Dennett speculated in *Kinds of Minds* 1996: "Perhaps the kind of mind you get when you add language to it is so different from the kind of mind you can have without language that calling them both minds is a mistake." Recent work in AI can be seen as testing Dennett's thesis by exploring the performance of AI systems with and without linguistic training. I argue that the success of Large Language Models at inferential reasoning, limited though it may be, supports Dennett's radical view about the effect of language on thought. I suggest it is the abstractness and efficiency of linguistic encoding that lies behind the capacity of LLMs to perform inferences across a wide range of domains. In a slogan, language makes inference computationally tractable. I assess what these results in AI indicate about the role of language in the workings of our own biological minds.
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。