# GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

arXiv: https://arxiv.org/abs/2601.18579 · HTML: https://mlsanity.com/paper/2601.18579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation](https://mlsanity.com/paper/2409.05591/) (2024)
- [GRAG: Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2405.16506/) (2024)
- [PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths](https://mlsanity.com/paper/2502.14902/) (2025)
- [Knowledge Graph-Guided Retrieval Augmented Generation](https://mlsanity.com/paper/2502.06864/) (2025)
- [PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers](https://mlsanity.com/paper/2406.12430/) (2024)
- [A Statutory Article Retrieval Dataset in French](https://mlsanity.com/paper/2108.11792/) (2021)
- [KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG](https://mlsanity.com/paper/2502.09304/) (2025)
- [HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses](https://mlsanity.com/paper/2312.15883/) (2023)
- [Adaptive Re-Ranking with a Corpus Graph](https://mlsanity.com/paper/2208.08942/) (2022)
- [The ACL OCL Corpus: Advancing Open Science in Computational Linguistics](https://mlsanity.com/paper/2305.14996/) (2023)
- [Guiding Retrieval using LLM-based Listwise Rankers](https://mlsanity.com/paper/2501.09186/) (2025)
- [LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2504.03137/) (2025)
- [LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs](https://mlsanity.com/paper/2409.12177/) (2024)
- [Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation](https://mlsanity.com/paper/2510.25518/) (2025)

## Abstract (arXiv)

Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing methods suffer from two critical blind spots, namely semantically blind graph expansion and topology blind pruning, or else rely on prohibitively slow retrieval and generation interleaving. To address this, we formalize these limitations through an operational taxonomy and propose a retriever design that couples semantics-aware adding with graph-aware pruning under efficiency constraints. We instantiate this design as GraFine, which alternates between two refinement stages: Semantic Proximity eXpansion (SPX) for semantics-aware node addition, and a Graph Smoothing Reranker (GSR) for graph-aware pruning. Experiments on reference networks and text-rich knowledge graphs show that GraFine improves retrieval accuracy and generation quality while maintaining time-efficiency. Furthermore, we introduce Topological Recall (TR), a metric that quantifies the topological proximity between retrieved and oracle nodes. Our analysis using TR confirms that GraFine more effectively steers refinement toward undiscovered oracle nodes by leveraging intermediate contextual clues. Our code is available at this link: https://github.com/asmath472/GraFine.