CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

TL;DR

CG-RAG introduces a novel graph-based retrieval framework that combines sparse and dense signals to improve scientific literature question answering with enhanced retrieval and generation quality.

Contribution

The paper presents a new framework integrating graph structures with hybrid retrieval signals and a context-aware generation strategy for research question answering.

Findings

Significantly outperforms existing RAG methods in retrieval accuracy.

Enhances generation quality with contextually enriched responses.

Demonstrates generalizability across multiple domains.

Abstract

Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with precise information retrieval. In this paper, we introduce Contextualized Graph Retrieval-Augmented Generation (CG-RAG), a novel framework that integrates sparse and dense retrieval signals within graph structures to enhance retrieval efficiency and subsequently improve generation quality for research question answering. First, we propose a contextual graph representation for citation graphs, effectively capturing both explicit and implicit connections within and across documents. Next, we introduce Lexical-Semantic Graph Retrieval (LeSeGR), which seamlessly integrates sparse and dense retrieval signals with graph encoding. It bridges the gap between lexical precision and semantic understanding in citation graph retrieval, demonstrating generalizability to existing graph retrieval and hybrid retrieval methods. Finally, we present a context-aware generation strategy that utilizes the retrieved graph-structured information to generate precise and contextually enriched responses using large language models (LLMs). Extensive experiments on research question answering benchmarks across multiple domains demonstrate that our CG-RAG framework significantly outperforms RAG methods combined with various state-of-the-art retrieval approaches, delivering superior retrieval accuracy and generation quality.