LLMs可能以无理性关联方式思考，而非传统理性思维。
How LLMs Might Think
- 提出LLMs可能通过非理性关联进行思维
- 认为其思维模式为纯关联性，非逻辑推理
- 适合对认知机制感兴趣的读者
大型语言模型是否具备思考能力？近期，Daniel Stoljar与Zhihe Vincent Zhang基于理性论据主张LLMs不具备思考能力。本文反驳该观点，指出理性论证存在漏洞，并揭示一个有趣的可能性：即LLMs仅进行非理性的、关联性的思维活动，拥有纯粹的关联性心智。我们的核心观点是，若LLMs确实具备思考能力，那很可能正是以这种非理性关联的方式进行。
原文摘要 · Abstract (English)
Do large language models (LLMs) think? Daniel Stoljar and Zhihe Vincent Zhang have recently developed an argument from rationality for the claim that LLMs do not think. We contend, however, that the argument from rationality not only falters, but leaves open an intriguing possibility: that LLMs engage only in arational, associative forms of thinking, and have purely associative minds. Our positive claim is that if LLMs think at all, they likely think precisely in this manner.
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。