Graph-based Retrieval-Augmented Generation (RAG) has shown great potential for improving multi-level reasoning and structured evidence aggregation. However, existing graph-based RAG frameworks heavily rely on exploiting large language models (LLMs) during indexing and querying, leading to high token consumption, computational cost and latency overhead. In this paper, we propose LiteSemRAG, a lightweight, fully LLM-free, semantic-aware graph retrieval framework. LiteSemRAG constructs a heterogeneous semantic graph by exploiting contextual token-level embeddings, explicitly separating surface lexical representations from context-dependent semantic meanings. To robustly model polysemy, we introduce a dynamic semantic node construction mechanism with chunk-level context aggregation and adaptive anomaly handling. At query stage, LiteSemRAG performs a two-step semantic-aware retrieval process that integrates co-occurrence graph weighting with an isolated semantic recovery mechanism, enabling balanced structural reasoning and semantic coverage. We evaluate LiteSemRAG on three benchmark datasets and experimental results show that LiteSemRAG achieves the best mean reciprocal rank (MRR@10) across all datasets and competitive or superior recall rate (Recall@10) compared to state-of-the-art LLM-based graph RAG systems. Meanwhile, LiteSemRAG consumes zero LLM tokens and achieves substantial efficiency improvements in both indexing and querying due to the elimination of LLM usage. These results demonstrate the effectiveness of LiteSemRAG, indicating that a strong semantic-aware graph retrieval framework can be achieved without relying on LLM-based approaches.
Figures & tables
Figure 1: Overview of the two-step semantic-aware retrieval process
Figure 2: Example of the multi-layer heterogeneous semantic graph index
Figure 3: Embedding distribution of strong contextual information (left), weak contextual information (middle), and after aggregation (right)
Model
HotpotQA
SciFact
Fever
Recall@10
MRR@10
Recall@10
MRR@10
Recall@10
MRR@10
GraphRAG (GPT)
55.9%
N/A
87.4%
N/A
45.8%
N/A
GraphRAG (LLaMA)
ETL
N/A
ETL
N/A
ETL
N/A
LightRAG (GPT)
71.5%
0.419
95.2%
0.427
84.6%
0.511
LightRAG (LLaMA)
69.3%
0.359
93.5%
0.361
86.2%
0.422
LiteSemRAG
73.5%
0.694
92.3%
0.692
88.3%
0.806
Table 1: Retrieval results on three datasets
HotpotQA
SciFact
Fever
Method
AIT
AQT
AIT
AQT
AIT
AQT
GraphRAG (GPT)
3.55s
29.8s
4.35s
48.76s
3.08s
30.66s
GraphRAG (LLaMA)
ETL
ETL
ETL
ETL
ETL
ETL
LightRAG (GPT)
7.98s
0.58s
10.31s
1.57s
7.71s
1.45s
LightRAG (LLaMA)
8.06s
1.72s
10.39s
1.33s
8.12s
1.13s
LiteSemRAG
0.24s
0.11s
0.69s
0.13s
0.47s
0.09s
Table 2: Indexing and query time efficiency comparison across datasets
HotpotQA
SciFact
Fever
Method
ITC
QTC
ITC
QTC
ITC
QTC
GraphRAG (GPT)
8.07K
10.85K
9.92K
11.24K
7.11K
4.06K
GraphRAG (LLaMA)
ETL
ETL
ETL
ETL
ETL
ETL
LightRAG (GPT)
7.30K
0.43K
9.32K
0.59K
8.58K
0.44K
LightRAG (LLaMA)
8.17K
0.47K
8.85K
0.56K
8.23K
0.45K
LiteSemRAG
0
0
0
0
0
0
Table 3: LLM token consumption comparison across datasets
Method
HotpotQA
SciFact
Fever
R@10
M@10
AQT
R@10
M@10
AQT
R@10
M@10
AQT
Broad search and reranking
32.5%
0.197
2.85s
14.9%
0.056
2.97s
46.7%
0.251
3.24s
Two-step semantic-aware
73.5%
0.694
0.24s
92.3%
0.692
0.69s
88.3%
0.806
0.47s
Table 4: Ablation study on two-step semantic-aware retrieval
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce indexing costs by leveraging Named Entity Recognition (NER), they rely strictly on structural co-occurrence, failing to capture latent semantic connections between disjoint entities. To address this, we propose EHRAG, a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic level relationships, employing a hybrid structural-semantic retrieval mechanism. Specifically, EHRAG constructs structural hyperedges based on sentence-level co-occurrence with lightweight entity extraction and semantic hyperedges by clustering entity text embeddings, ensuring the hypergraph encompasses both structural and semantic information. For retrieval, EHRAG performs a structure-semantic hybrid diffusion with topic-aware scoring and personalized pagerank (PPR) refinement to identify the top-k relevant documents. Experiments on four datasets show that EHRAG outperforms state-of-the-art baselines while maintaining linear indexing complexity and zero token consumption for construction. Code is available at https://github.com/yfsong00/EHRAG.
Yifan Song, Xingjian Tao, Zhicheng Yang +2
1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology
Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction. On DistComp, a benchmark for multi-hop retrieval over distributed-systems papers, LiteRAG attains the highest overall quality among the evaluated methods (0.798) while reducing per-query latency by over 100× and cost by over 99% relative to GraphRAG Global and DRIFT. On UltraDomain, it matches LinearRAG on overall quality while using about 14× fewer tokens. An ablation study indicates that LiteRAG's query-adaptive thresholding and community-aware hub penalization are the main drivers of its token-efficiency gains.
Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge. However, standard RAG approaches struggle with multi-hop reasoning. While recent graph-based RAG methods improve the retrieval of interconnected chunks, they often rely on computationally expensive and error-prone LLM-based extraction pipelines. To address these issues, we propose TIGRAG (Token-Induced GraphRAG), an efficient graph-augmented RAG framework based on a token co-occurrence Knowledge Graph. TIGRAG directly models topological relationships between tokens using sliding-window co-occurrence statistics, thus enabling scalable graph construction. During inference, it combines graph-based semantic expansion and neural reranking to retrieve interconnected evidence for multi-hop reasoning. Specifically, it introduces an iterative entity-driven retrieval strategy that progressively expands the query using bridging entities extracted from previously retrieved contexts. We evaluated TIGRAG on three widely adopted multi-hop Question Answering (QA) benchmarks. Experimental results demonstrated that our framework consistently outperforms dense retrieval and graph-based RAG methods in both retrieval and downstream QA tasks, while substantially reducing indexing time, inference latency, and prompt footprint.
Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5
aUniversità Politecnica delle Marche, Ancona, Italy · bUniversità di Modena e Reggio Emilia, Modena, Italy