Xiaofang ZHOU

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

2026 · Rare & Special e-Zone (The Hong Kong University of Science and Technology)

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 …