1
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
揭秘RAG中LLM引用生成的内在机制，让AI“引经据典”不再黑箱。
arXiv:2606.28358v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (L…