Large Language Models (LLMs) are prone to hallucination, the generation of plausible yet factually incorrect statements. This work investigates the intrinsic, architectural origins of this failure mode through three primary contributions.First, to enable the reliable tracing of internal semantic failures, we propose \textbf{Distributional Semantics Tracing (DST)}, a unified framework that integrates established interpretability techniques to produce a causal map of a model's reasoning, treating meaning as a function of context (distributional semantics). Second, we pinpoint the model's layer at which a hallucination becomes inevitable, identifying a specific \textbf{commitment layer} where a model's internal representations irreversibly diverge from factuality. Third, we identify the underlying mechanism for these failures. We observe a conflict between distinct computational pathways, which we interpret using the lens of dual-process theory: a fast, heuristic \textbf{associative pathway} (akin to System 1) and a slow, deliberate \textbf{contextual pathway} (akin to System 2), leading to predictable failure modes such as \textit{Reasoning Shortcut Hijacks}. Our framework's ability to quantify the coherence of the contextual pathway reveals a strong negative correlation ($\rho = -0.863$) with hallucination rates, implying that these failures are predictable consequences of internal semantic weakness. The result is a mechanistic account of how, when, and why hallucinations occur within the Transformer architecture.

翻译：暂无翻译