Augmenting Question Answering with A Hybrid RAG Approach
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_ | 1866912848223928320 |
|---|---|
| author | Yang, Tianyi Haque, Nashrah Jonnalagadda, Vaishnave Ong, Yuya Jeremy Chen, Zhehui Wu, Yanzhao Yu, Lei Jadav, Divyesh Wei, Wenqi |
| author_facet | Yang, Tianyi Haque, Nashrah Jonnalagadda, Vaishnave Ong, Yuya Jeremy Chen, Zhehui Wu, Yanzhao Yu, Lei Jadav, Divyesh Wei, Wenqi |
| contents | Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually relevant information, leading to incomplete or suboptimal answers. In this paper, we introduce Structured-Semantic RAG (SSRAG), a hybrid architecture that enhances QA quality by integrating query augmentation, agentic routing, and a structured retrieval mechanism combining vector and graph based techniques with context unification. By refining retrieval processes and improving contextual grounding, our approach improves both answer accuracy and informativeness. We conduct extensive evaluations on three popular QA datasets, TruthfulQA, SQuAD and WikiQA, across five Large Language Models (LLMs), demonstrating that our proposed approach consistently improves response quality over standard RAG implementations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12658 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Augmenting Question Answering with A Hybrid RAG Approach Yang, Tianyi Haque, Nashrah Jonnalagadda, Vaishnave Ong, Yuya Jeremy Chen, Zhehui Wu, Yanzhao Yu, Lei Jadav, Divyesh Wei, Wenqi Computation and Language Artificial Intelligence Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually relevant information, leading to incomplete or suboptimal answers. In this paper, we introduce Structured-Semantic RAG (SSRAG), a hybrid architecture that enhances QA quality by integrating query augmentation, agentic routing, and a structured retrieval mechanism combining vector and graph based techniques with context unification. By refining retrieval processes and improving contextual grounding, our approach improves both answer accuracy and informativeness. We conduct extensive evaluations on three popular QA datasets, TruthfulQA, SQuAD and WikiQA, across five Large Language Models (LLMs), demonstrating that our proposed approach consistently improves response quality over standard RAG implementations. |
| title | Augmenting Question Answering with A Hybrid RAG Approach |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.12658 |