Improving Groundedness in Policy Document Question Answering Using Hybrid RAG with Structure-Based Topic Chunking : A DTNN 2030 Case Study
This paper presents a Hybrid Retrieval-Augmented Generation (RAG) framework for question answering on long-form policy documents. Dense-only retrieval, a common baseline in RAG pipelines, may struggle with exact lexical matching for structured information such as technical terminology, acronyms, and domain-specific ent...