Source: Microsoft Research: LazyGraphRAG
Microsoft Research blog on LazyGraphRAG, which defers LLM work to query time and indexes at about vector-RAG cost.
Contents
- What: vendor research blog post
- Author: Microsoft Research
- Date: 2024-11-25 (editor’s note 2025-06-06)
- Original: LazyGraphRAG: Setting a new standard for quality and cost
Summary
Presents a GraphRAG variant that builds its concept graph with cheap NLP noun-phrase extraction instead of LLM summarization, and spends LLM calls only at query time under a tunable relevance-test budget.
Key claims
- Indexing cost equals vector RAG and is about 0.1% of full GraphRAG.
- Query: best-first (vector similarity) plus breadth-first community search with iterative deepening and an LLM relevance assessor.
- Matches GraphRAG global search quality on global queries at over 700x lower query cost; at 4% of its query cost beats all compared methods on local and global queries.
- Evaluated on 5,590 AP news articles with 100 synthetic queries, judged by an LLM.
- A single relevance-test budget parameter trades cost for quality.