Don't Forget to Connect! Improving RAG with Graph-based Reranking
Jialin Dong, Bahare Fatemi, Bryan Perozzi, Lin F. Yang, Anton, Tsitsulin

TL;DR
This paper introduces G-RAG, a graph neural network-based reranker that enhances retrieval-augmented generation by leveraging document connections and semantic graphs, outperforming existing methods with lower computational costs.
Contribution
We propose G-RAG, a novel graph neural network reranker that integrates document connections and semantic information to improve RAG performance.
Findings
G-RAG outperforms state-of-the-art rerankers in RAG tasks.
G-RAG has a smaller computational footprint than competing methods.
PaLM 2 underperforms as a reranker compared to G-RAG.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsContext-Aware Activity Recognition Systems · Gaze Tracking and Assistive Technology · Robotics and Automated Systems
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · WordPiece · Linear Warmup With Linear Decay · Weight Decay · Attention Dropout · Linear Layer · Byte Pair Encoding · Adam · Residual Connection
