GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
This addresses inefficiencies in retrieval for RAG systems, particularly when evidence is scattered, offering a retriever-agnostic solution with low latency, though it appears incremental as it builds on prior graph-based and agentic methods.
The paper tackles the problem of insufficient semantic search in retrieval-augmented generation systems for complex information needs by proposing GraphER, a graph-based enrichment and reranking method that captures multiple forms of proximity beyond semantic similarity, resulting in improved retrieval effectiveness as demonstrated in experiments on multiple benchmarks.
Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources. Prior approaches to this problem include agentic retrieval strategies, which expand the semantic search space by generating additional queries. However, these methods do not fully leverage the organizational structure of the data and instead rely on iterative exploration, which can lead to inefficient retrieval. Another class of approaches employs knowledge graphs to model non-semantic relationships through graph edges. Although effective in capturing richer proximities, such methods incur significant maintenance costs and are often incompatible with the vector stores used in most production systems. To address these limitations, we propose GraphER, a graph-based enrichment and reranking method that captures multiple forms of proximity beyond semantic similarity. GraphER independently enriches data objects during offline indexing and performs graph-based reranking over candidate objects at query time. This design does not require a knowledge graph, allowing GraphER to integrate seamlessly with standard vector stores. In addition, GraphER is retriever-agnostic and introduces negligible latency overhead. Experiments on multiple retrieval benchmarks demonstrate the effectiveness of the proposed approach.