> GraphIndex: Incremental Multi-Modal KG Indexing Without LLMs

Information Retrieval 高级 2026-04-01 06:41 2026-04-01
#knowledge graphs #retrieval #incremental indexing #RAG #BM25 #semantic search #hybrid fusion

Three fused index modalities (structural, semantic, relational) with cross-modal incremental propagation: 10-19x rebuild speedups, beating BM25 on all 5 BEIR benchmarks, no LLM at index time. 169K papers at 1.16M edges.

GraphIndex: Incremental Multi-Modal KG Indexing

No LLM Required at Index Time

System LLM at Index Incremental Multi-Modal
LightRAG Yes Partial No
Microsoft GraphRAG Yes No No
GraphIndex No Yes Yes

LightRAG: 738s for 500 docs (with LLM). GraphIndex: 640s for 5,000 docs (no LLM). 10x throughput with 10x larger corpus.

Incremental Speedups

Dataset Speedup
SciFact (5.2K) ~10x
arXiv-5K ~14x
ogbn-arxiv (169K papers, 1.16M edges) ~19x

Speedup grows with corpus size: incremental delta is roughly constant.

Hybrid RRF Results

P@10 = 0.636 (BM25 + Semantic + Structural) on arXiv-5K. Semantic modality outperformed BM25 on all 5 BEIR benchmarks (p < 0.001).

RAG End-to-End (SciFact, 300 claims)

Retriever Llama-3.1-8B Accuracy
BM25 37.7%
Semantic (GraphIndex) 43.3%

Domain Adapter Pattern

244-851 LOC to add a new domain (code, scientific literature, markdown already implemented). A weekend engineering task, not a research project.

Key Lesson

Hybrid fusion is context-sensitive: structural modality adds value for graph-native queries but contributes little for purely semantic retrieval. Always run modality ablations.