1
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
从线性化表示角度拆解大模型在结构化知识上产生幻觉的深层机理，ACL 2026论文揭示推理缺陷。
arXiv:2605.26362v1 Announce Type: cross Abstract: In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as…