graph-rag

ISO-RAG is a training-free, topology-driven retrieval-augmented generation framework that uses isoperimetric noise control to improve multi-hop question answering by reducing semantic drift and enhancing efficiency.

RegDivergence-101 is a pilot benchmark for detecting cross-jurisdiction regulatory contradictions between FDA and EMA using LLMs, establishing baseline methods with varying performance in classifying regulatory relationships.

Microsoft Research's LazyGraphRAG outperformed vector RAG on data-local questions across 8k, 120k, and million-token contexts, winning 92/90/91% at a tenth of the cost, and is now open-sourced on GitHub.

This paper introduces HCG-RAG, which uses schema-constrained causal graphs for retrieval-augmented generation, achieving 3-20x fewer nodes and 8x-135x fewer LLM calls while matching or exceeding baseline answer quality on medical benchmarks.

This paper proposes improvements to HyperGraphRAG by using self-consistency prompting for better fact extraction and Personalized PageRank for enhanced chunk retrieval.

A novel framework called FAIR GraphRAG integrates FAIR Digital Objects with graph-based retrieval to enhance retrieval-augmented generation for semantic data analysis, improving question answering accuracy and adherence to FAIR principles, demonstrated on a biomedical dataset.

A clear explanation of Standard RAG, Graph RAG, and Agentic RAG, covering their differences, use cases, and how they handle single-hop vs. multi-hop queries.

This paper proposes HyGRAG, a hierarchical graph RAG framework that integrates contextual and relational information for multi-hop reasoning, achieving a 9.7% average accuracy improvement over existing methods.

FlowRAG proposes a novel semantic-aware retrieval framework that constructs a quad-level heterogeneous graph and uses frequency-aware weighted flow to extract explicit reasoning paths, achieving state-of-the-art performance on complex reasoning benchmarks.

Kwipu is a new open-source local Graph RAG system that indexes Markdown and Obsidian notes into a property graph, enabling natural-language queries with hybrid retrieval and supporting local LLMs via Ollama.

The author shares experience in using the open-source tool CodeGraph to build a local knowledge graph for a codebase, compares the differences between RAG and knowledge graphs, and demonstrates how the graph reduces tool calls by 94% and saves 35% on tokens, greatly improving development efficiency.

Introduces Narrative Knowledge Weaver (NKW), a source-grounded framework for narrative-centric retrieval-augmented reasoning in long-form text understanding. It aligns textual evidence, atomic facts, graph structure, entity profiles, and storylines, achieving strong results on screenplay-level story-world QA benchmarks.

This paper compares two strategies for injecting structured biomedical knowledge from the UMLS Metathesaurus into language models: continual pretraining (embedding knowledge into model parameters) and GraphRAG (querying a knowledge graph at inference time). Results show improvements on biomedical QA benchmarks, with GraphRAG on LLaMA 3-8B yielding over 3 and 5 accuracy points on PubMedQA and BioASQ respectively without any retraining.

Code-Graph-RAG is an open-source tool that parses multi-language codebases with Tree-sitter, builds a knowledge graph in Memgraph, and lets you query, edit, and optimize code using plain English. It supports monorepos with mixed languages under a unified graph schema.