EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
Fangyuan Zhang, Zhengjun Huang, Yingli Zhou, Qintian Guo, Zhixun Li, Wensheng Luo, Di Jiang, Yixiang Fang, Xiaofang Zhou

TL;DR
EraRAG introduces a scalable, efficient framework for dynamic retrieval-augmented generation that supports incremental updates over growing corpora without retraining, maintaining high accuracy and low latency.
Contribution
It proposes a multi-layered Graph-RAG framework using LSH for hierarchical corpus partitioning, enabling efficient localized updates and improved scalability in dynamic environments.
Findings
Achieves up to tenfold reduction in update time and token consumption.
Maintains high retrieval accuracy with dynamic corpus updates.
Demonstrates superior performance on large-scale benchmarks.
Abstract
Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typically assume a static corpus, requiring expensive full-graph reconstruction whenever new documents arrive, limiting their scalability in dynamic, evolving environments. To address these limitations, we introduce EraRAG, a novel multi-layered Graph-RAG framework that supports efficient and scalable dynamic updates. Our method leverages hyperplane-based Locality-Sensitive Hashing (LSH) to partition and organize the original corpus into hierarchical graph structures, enabling efficient and localized insertions of new data without disrupting the existing topology. The design eliminates the need for retraining or costly recomputation while preserving high retrieval accuracy and low latency. Experiments on large-scale…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Speech Recognition and Synthesis
MethodsLinear Warmup With Linear Decay · Refunds@Expedia|||How do I get a full refund from Expedia? · Attention Dropout · Byte Pair Encoding · Dense Connections · Softmax · Layer Normalization · Dropout · BERT · BART
