DOI : https://doi.org/10.62527/comien.3.1.56

Hybrid Sparse-Dense Retrieval-Augmented Generation: An Empirical Analysis with SPLADE and DPR

Rathinasamy Muthusami (1), Saritha K (2)
(1) Department of Computer Applications, Dr. Mahalingam College of Engineering and Technology, Pollachi, Tamil Nadu, India
(2) Department of Mathematics, P. A. College of Engineering and Technology, Pollachi, Tamil Nadu, India
Fulltext View | Download
How to cite (COMIEN) :
Muthusami, R., & Saritha, K. (2026). Hybrid Sparse-Dense Retrieval-Augmented Generation: An Empirical Analysis with SPLADE and DPR. International Journal on Computational Engineering, 3(1), 10–19. https://doi.org/10.62527/comien.3.1.56
Citation Format :

Retrieval-Augmented Generation (RAG) has become a key technique in open-domain question answering (QA), where a retriever fetches relevant documents that are passed to a language model to generate answers. Traditional retrievers like BM25 rely on exact lexical matches, while dense retrievers such as DPR capture semantic meaning but often struggle with specific terminology and interpretability. To address these limitations, this paper explores the use of SPLADE, a sparse lexical and expansion-based retriever, within a full RAG pipeline. We benchmark SPLADE against BM25 and DPR using datasets from the BEIR benchmark suite, such as FiQA and TREC-COVID. SPLADE consistently outperforms its counterparts in both retrieval and answer generation quality. For example, in FiQA, SPLADE achieves an nDCG@10 of 0.635, compared to 0.591 for BM25 and 0.604 for DPR. In downstream QA evaluation, using GPT-3.5 for generation, SPLADE-based retrieval leads to higher ROUGE-L scores (0.479) than BM25 (0.391) and DPR (0.418), reflecting more accurate and complete answers. To further enhance performance, we implement a hybrid retriever by combining SPLADE and DPR using Reciprocal Rank Fusion (RRF). This hybrid model achieves even stronger retrieval performance (nDCG@10: 0.681, Recall@10: 0.805), demonstrating that sparse and dense signals are complementary. Additionally, SPLADE offers interpretability via token-level expansion visualization, allowing for analysis of which terms influence retrieval. Our findings confirm that SPLADE, especially when combined with dense retrieval, significantly improves the effectiveness and transparency of LLM-based QA systems, paving the way for more accurate and explainable RAG architectures.

M. AL-Smadi, "QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning," in Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, Association for Computational Linguistics, 2025, pp. 892–898. doi:10.18653/v1/2025.arabicnlp-sharedtasks.123.

G. Izacard and E. Grave, "Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering," in Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Association for Computational Linguistics, 2021, pp. 874–880. doi:10.18653/v1/2021.eacl-main.74.

F. Petroni et al., "KILT: a Benchmark for Knowledge Intensive Language Tasks," in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, 2021, pp. 2523–2544. doi:10.18653/v1/2021.naacl-main.200.

Y. Li, N. Yang, L. Wang, F. Wei, and W. Li, "Generative retrieval for conversational question answering," Inf. Process. Manag., vol. 60, no. 5, p. 103475, Sep. 2023. doi:10.1016/j.ipm.2023.103475.

S. Robertson and H. Zaragoza, "The Probabilistic Relevance Framework: BM25 and Beyond," Found. Trends Inf. Retr., vol. 4, no. 1–2, pp. 1–174, Sep. 2009. doi:10.1561/1500000019.

Y. Lv and C. Zhai, "When documents are very long, BM25 fails!," in Proc. 34th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., ACM, Jul. 2011, pp. 1103–1104. doi:10.1145/2009916.2010070.

N. Thakur, N. Reimers, A. Rücklé, A. Srivastava, and I. Gurevych, "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models," 2021, arXiv:2104.08663. doi: 10.48550/arXiv.2104.08663.

V. Karpukhin et al., "Dense Passage Retrieval for Open-Domain Question Answering," in Proc. 2020 Conf. Empir. Methods Nat. Lang. Process. (EMNLP), Association for Computational Linguistics, 2020, pp. 6769–6781. doi:10.18653/v1/2020.emnlp-main.550.

L. Xiong et al., "Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval," 2020, arXiv:2007.00808. doi:10.48550/arXiv.2007.00808.

L. Gao and J. Callan, "Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval," in Proc. 60th Annu. Meet. Assoc. Comput. Linguist. (Vol. 1: Long Papers), Association for Computational Linguistics, 2022, pp. 2843–2853. doi:10.18653/v1/2022.acl-long.203.

M. A. K. Ayoub, Z. Su, and Q. Li, "A Case Study of Enhancing Sparse Retrieval using LLMs," in Companion Proc. ACM Web Conf. 2024, ACM, May 2024, pp. 1609–1615. doi: 10.1145/3589335.3651945.

N. Reimers and I. Gurevych, "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks," in Proc. 2019 Conf. Empir. Methods Nat. Lang. Process. 9th Int. Jt. Conf. Nat. Lang. Process. (EMNLP-IJCNLP), Association for Computational Linguistics, 2019, pp. 3980–3990. doi:10.18653/v1/d19-1410.

T. Formal, B. Piwowarski, and S. Clinchant, "SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking," in Proc. 44th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., ACM, Jul. 2021, pp. 2288–2292. doi:10.1145/3404835.3463098.

T. Formal, C. Lassance, B. Piwowarski, and S. Clinchant, "Towards Effective and Efficient Sparse Neural Information Retrieval," ACM Trans. Inf. Syst., vol. 42, no. 5, pp. 1–46, Apr. 2024. doi:10.1145/3634912.

T. Formal, C. Lassance, B. Piwowarski, and S. Clinchant, "SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval," 2021, arXiv:2109.10086. doi: 10.48550/arXiv.2109.10086.

P. Mandikal and R. Mooney, "Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval," 2024, arXiv:2401.04055. doi: 10.48550/arXiv.2401.04055.

M. G. Arivazhagan et al., "Hybrid Hierarchical Retrieval for Open-Domain Question Answering," in Findings of the Association for Computational Linguistics: ACL 2023, Association for Computational Linguistics, 2023, pp. 10680–10689. doi:10.18653/v1/2023.findings-acl.679.

S. Ghosh and P. Rigollet, "Sparse Multi-Reference Alignment: Phase Retrieval, Uniform Uncertainty Principles and the Beltway Problem," Found. Comput. Math., vol. 23, no. 5, pp. 1851–1898, Aug. 2022. doi:10.1007/s10208-022-09584-6.

S. Samuel et al., "MMMORRF: Multimodal Multilingual MOdularized Reciprocal Rank Fusion," in Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul. 2025, pp. 4004–4009. doi:10.1145/3726302.3730157.

S. Bruch, S. Gai, and A. Ingber, "An Analysis of Fusion Functions for Hybrid Retrieval," ACM Trans. Inf. Syst., vol. 42, no. 1, pp. 1–35, Aug. 2023. doi:10.1145/3596512.

Z. Yang et al., "An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities," ACM Trans. Softw. Eng. Methodol., Feb. 2025. doi:10.1145/3717061.

J. Seo et al., "Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions," Mathematics, vol. 10, no. 8, p. 1335, Apr. 2022. doi:10.3390/math10081335.

R. Nogueira, W. Yang, J. Lin, and K. Cho, "Document Expansion by Query Prediction," 2019, arXiv:1904.08375. doi:10.48550/arXiv.1904.08375.

S. Basnet, J. Gou, A. Mallia, and T. Suel, "DeeperImpact: Optimizing Sparse Learned Index Structures," 2024, arXiv:2405.17093. doi:10.48550/arXiv.2405.17093.

A. Mallia, O. Khattab, T. Suel, and N. Tonellotto, "Learning Passage Impacts for Inverted Indexes," in Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul. 2021, pp. 1723–1727. doi:10.1145/3404835.3463030.

O. Khattab and M. Zaharia, "ColBERT," in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul. 2020, pp. 39–48. doi:10.1145/3397271.3401075.

C.-W. Huang and Y.-N. Chen, "PairDistill: Pairwise Relevance Distillation for Dense Retrieval," in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2024, pp. 18225–18237. doi:10.18653/v1/2024.emnlp-main.1013.

R. Ren et al., "RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking," in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2021, pp. 2825–2835. doi:10.18653/v1/2021.emnlp-main.224.

J. Zhan et al., "Optimizing Dense Retrieval Model Training with Hard Negatives," in Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul. 2021, pp. 1503–1512. doi:10.1145/3404835.3462880.

L. Gao, Z. Dai, and J. Callan, "COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List," in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, 2021, pp. 3030–3042. doi:10.18653/v1/2021.naacl-main.241.

S. MacAvaney, A. Cohan, and N. Goharian, "SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search," in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, 2020, pp. 4171–4179. doi:10.18653/v1/2020.emnlp-main.341.

Q. Lyu et al., "Faithful Chain-of-Thought Reasoning," in Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, 2023, pp. 305–329. doi:10.18653/v1/2023.ijcnlp-main.20.

S. Rakin, M. A. R. Shibly, Z. M. Hossain, M. M. Akbar, and Z. Khan, "Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and for Hallucination Reduction," in Advances in Intelligent Systems and Computing, Springer Nature Switzerland, 2025, pp. 482–493. doi:10.1007/978-3-031-89063-5_42.

B. Yuan, "FinBERT-QA: Financial Question Answering with Pre-Trained BERT Language Models," 2025, arXiv:2505.00725. doi:10.48550/arXiv.2505.00725.

C. Malaviya et al., "ExpertQA: Expert-Curated Questions and Attributed Answers," in Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Association for Computational Linguistics, 2024, pp. 3025–3045. doi:10.18653/v1/2024.naacl-long.167.

W. Shi et al., "REPLUG: Retrieval-Augmented Black-Box Language Models," in Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Association for Computational Linguistics, 2024, pp. 8371–8384. doi:10.18653/v1/2024.naacl-long.463.

M. S. Rashid, J. A. Meem, Y. Dong, and V. Hristidis, "Progressive Query Expansion for Retrieval Over Cost-Constrained Data Sources," 2024, arXiv:2406.07136. doi: 10.48550/arXiv.2406.07136.