作者位次 #4/8ACL 2026Poster· Natural Language Processing
Why LLM s Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
Shanghao Li · Jinda Han · Yibo Wang · Yuanjie Zhu · Zihe Song · Langzhou He · Kenan Kamel A Alghythee · Philip S. Yu
摘要
In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is available, LLMs can still produce hallucinated outputs, and the u...