Retrieval Augmented Generation (RAG) has greatly improved the performance of
Large Language Model (LLM) responses by grounding generation with context from
existing documents. These systems work well when documents are clearly relevant
to a question context. But what about when a document has partial information,
or less obvious connections to the context? And how should we reason about
connections between documents? In this work, we seek to answer these two core
questions about RAG generation. We introduce G-RAG, a reranker based on graph
neural networks (GNNs) between the retriever and reader in RAG. Our method
combines both connections between documents and semantic information (via
Abstract Meaning Representation graphs) to provide a context-informed ranker
for RAG. G-RAG outperforms state-of-the-art approaches while having smaller
computational footprint. Additionally, we assess the performance of PaLM 2 as a
reranker and find it to significantly underperform G-RAG. This result
emphasizes the importance of reranking for RAG even when using Large Language
Models.

G-RAG is a graph neural network-based reranker that combines connections between documents and semantic information to improve the performance of Large Language Model-based Retrieval Augmented Generation (RAG) systems.