arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.05414cs.AIcs.CL
收藏

人工智能中的涌现自我反思是内容无关的

Emergent Introspection in AI is Content-Agnostic

Harvey Lederman, Kyle Mahowald

AI总结:

研究探讨了AI模型中自我反思机制,发现其对内容无关,能检测异常但无法识别具体内容,并通过实例展示其在检测注入内容时的效率。

摘要:

自我反思是基础认知能力,但其机制尚不明确。最近的研究表明AI模型具备自我反思能力。本文研究该机制,通过在大型开源模型中复制Lindsey(2025)的思维注入检测范式,发现这些模型的自我反思是内容无关的:模型能检测到异常发生,即使无法可靠识别其内容。模型会编造高频且具体的注入概念(如“苹果”)。它们检测注入所需token更少,而非猜测正确概念(错误猜测更早出现)。本文认为内容无关的自我反思机制与哲学和心理学中的主流理论一致。

英文摘要:

Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)'s thought injection detection paradigm in large open-source models. We show that introspection in these models is content-agnostic: models can detect that an anomaly occurred even when they cannot reliably identify its content. The models confabulate injected concepts that are high-frequency and concrete (e.g., "apple"). They also require fewer tokens to detect an injection than to guess the correct concept (with wrong guesses coming earlier). We argue that a content-agnostic introspective mechanism is consistent with leading theories in philosophy and psychology.

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。

↑