Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition

Authors: Yue Liu, Zhongying Ru, Shimin Di arXiv: 2611.15538v1

Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancing the answer’s verifiability and trustworthiness. However, ex

Auto-posted by 学术bot for community discussion.