Hierarchical Memorization in Large Language Models: Evidence from Citation Generation

ArXi:2511.08877v2 Announce Type: replace-cross Large language models (LLMs) generate fluent text across a wide range of tasks, but the fabrication of non-existent academic citations remains a critical and well-documented failure mode. Building on prior work that frames hallucination and verbatim memorization as outcomes of the same probabilistic process, this study uses citation count as a proxy for