# Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval

arXiv: https://arxiv.org/abs/2506.08074 · HTML: https://mlsanity.com/paper/2506.08074/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 13 of 13)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval](https://mlsanity.com/paper/2312.15503/) (2023)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Reasoning over Public and Private Data in Retrieval-Based Systems](https://mlsanity.com/paper/2203.11027/) (2022)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [Graph Attention with Hierarchies for Multi-hop Question Answering](https://mlsanity.com/paper/2301.11792/) (2023)

## Built on by (most cited first, 7 of 7)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [VistaHop: Benchmarking Long-Horizon Visual DeepSearch](https://mlsanity.com/paper/2606.03273/) (2026)
- [Core-based Hierarchies for Efficient GraphRAG](https://mlsanity.com/paper/2603.05207/) (2026)
- [Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG](https://mlsanity.com/paper/2603.07179/) (2026)
- [Query-Centric Graph Retrieval Augmented Generation](https://mlsanity.com/paper/2509.21237/) (2025)
- [StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.25379/) (2026)
- [CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval](https://mlsanity.com/paper/2606.28365/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph (HLG), a three-tier index that (i) traces every atomic proposition to its source, (ii) clusters propositions into latent topics, and (iii) links entities and relations to expose cross-document paths. On top of HLG we build two complementary, plug-and-play retrievers: StatementGraphRAG, which performs fine-grained entity-aware beam search over propositions for high-precision factoid questions, and TopicGraphRAG, which selects coarse topics before expanding along entity links to supply broad yet relevant context for exploratory queries. Additionally, existing benchmarks lack the complexity required to rigorously evaluate multi-hop summarization systems, often focusing on single-document queries or limited datasets. To address this, we introduce a synthetic dataset generation pipeline that curates realistic, multi-document question-answer pairs, enabling robust evaluation of multi-hop retrieval systems. Extensive experiments across five datasets demonstrate that our methods outperform naive chunk-based RAG achieving an average relative improvement of 23.1% in retrieval recall and correctness. Open-source Python library is available at https://github.com/awslabs/graphrag-toolkit.