G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

TL;DR

G-Retriever introduces a retrieval-augmented generation framework for conversational question answering on textual graphs, enabling effective, scalable, and hallucination-resistant understanding across diverse real-world applications.

Contribution

It develops the first RAG approach for textual graphs, formulates graph retrieval as a Steiner Tree problem, and creates a new benchmark for graph question answering.

Findings

Outperforms baselines on multiple textual graph tasks.

Scales effectively with larger graphs.

Reduces hallucinations in generated responses.

Abstract

Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface. In response to a user's questions, our method provides textual replies and highlights the relevant parts of the graph. While existing works integrate large language models (LLMs) and graph neural networks (GNNs) in various ways, they mostly focus on either conventional graph tasks (such as node, edge, and graph classification), or on answering simple graph queries on small or synthetic graphs. In contrast, we develop a flexible question-answering framework targeting real-world textual graphs, applicable to multiple applications including scene graph understanding, common sense reasoning, and knowledge graph reasoning. Toward this goal, we first develop a Graph Question Answering (GraphQA) benchmark with data collected from different tasks. Then, we propose our G-Retriever method, introducing the first retrieval-augmented generation (RAG) approach for general textual graphs, which can be fine-tuned to enhance graph understanding via soft prompting. To resist hallucination and to allow for textual graphs that greatly exceed the LLM's context window size, G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem. Empirical evaluations show that our method outperforms baselines on textual graph tasks from multiple domains, scales well with larger graph sizes, and mitigates hallucination.~\footnote{Our codes and datasets are available at: \url{https://github.com/XiaoxinHe/G-Retriever}}