大语言模型中理解机制的指示器
Mechanistic Indicators of Understanding in Large Language Models
AI总结：
本文提出一个分层框架，探讨大语言模型中理解的三个层次，通过机制可解释性揭示AI理解的机制与人类认知的异同。
摘要：
大语言模型（LLMs）通常被描绘为仅仅模仿语言模式而没有真正的理解。我们主张，最近在机制可解释性（MI）领域的发现，这一新兴领域探索LLMs的内部运作，使这种观点日益站不住脚——但只有在这些发现被整合到对理解的理论解释中时才成立。我们提出一个分层框架来思考LLMs中的理解，并利用它综合目前最相关的发现。该框架区分了三种层次化的理解类型，每种都对应于一个计算组织层次：概念理解出现于模型形成
英文摘要：
Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of LLMs, render this picture increasingly untenable--but only once those findings are integrated within a theoretical account of understanding. We propose a tiered framework for thinking about understanding in LLMs and use it to synthesize the most relevant findings to date. The framework distinguishes three hierarchical varieties of understanding, each tied to a corresponding level of computational organization: conceptual understanding emerges when a model forms "features" as directions in latent space, learning connections between diverse manifestations of a single entity or property; state-of-the-world understanding emerges when a model learns contingent factual connections between features and dynamically tracks changes in the world; principled understanding emerges when a model ceases to rely on memorized facts and discovers a compact "circuit" connecting these facts. Across these tiers, MI uncovers internal organizations that can underwrite understanding-like unification. However, these also diverge from human cognition in their parallel exploitation of heterogeneous mechanisms. Fusing philosophical theory with mechanistic evidence thus allows us to transcend binary debates over whether AI understands, paving the way for a comparative, mechanistically grounded epistemology that explores how AI understanding aligns with--and diverges from--our own.
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。
