Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918380516147200 |
|---|---|
| author | Amamou, Hazem Gagnon, Stéphane Davoust, Alan Avila, Anderson R. |
| author_facet | Amamou, Hazem Gagnon, Stéphane Davoust, Alan Avila, Anderson R. |
| contents | Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps reduce factual hallucinations and enables access to new information not available during pretraining. However, inconsistent retrieved information can negatively affect LLM responses. The Retrieval-Augmented Generation Benchmark (RGB) was introduced to evaluate the robustness of RAG systems under such conditions. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: noise robustness, information integration, negative rejection, and counterfactual robustness. We perform a comparative analysis between the RGB RAG baseline and GraphRAG, a knowledge graph based retrieval system. We test three GraphRAG customizations to improve robustness. Results show improvements over the RGB baseline and provide insights for designing more reliable RAG systems for real world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05698 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis Amamou, Hazem Gagnon, Stéphane Davoust, Alan Avila, Anderson R. Computation and Language 68T50, 68T30 I.2.7; H.3.3; I.2.4 Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps reduce factual hallucinations and enables access to new information not available during pretraining. However, inconsistent retrieved information can negatively affect LLM responses. The Retrieval-Augmented Generation Benchmark (RGB) was introduced to evaluate the robustness of RAG systems under such conditions. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: noise robustness, information integration, negative rejection, and counterfactual robustness. We perform a comparative analysis between the RGB RAG baseline and GraphRAG, a knowledge graph based retrieval system. We test three GraphRAG customizations to improve robustness. Results show improvements over the RGB baseline and provide insights for designing more reliable RAG systems for real world scenarios. |
| title | Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis |
| topic | Computation and Language 68T50, 68T30 I.2.7; H.3.3; I.2.4 |
| url | https://arxiv.org/abs/2603.05698 |