# A Study on the Efficiency and Generalization of Light Hybrid Retrievers

arXiv: https://arxiv.org/abs/2210.01371 · HTML: https://mlsanity.com/paper/2210.01371/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [Learning Dense Representations of Phrases at Scale](https://mlsanity.com/paper/2012.12624/) (2020)
- [Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index](https://mlsanity.com/paper/1906.05807/) (2019)
- [Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?](https://mlsanity.com/paper/2110.06918/) (2021)
- [Efficient Passage Retrieval with Hashing for Open-domain Question Answering](https://mlsanity.com/paper/2106.00882/) (2021)
- [A Replication Study of Dense Passage Retriever](https://mlsanity.com/paper/2104.05740/) (2021)
- [Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance](https://mlsanity.com/paper/2108.00644/) (2021)
- [Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators](https://mlsanity.com/paper/2111.13057/) (2021)
- [Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models](https://mlsanity.com/paper/2201.10582/) (2022)
- [Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness](https://mlsanity.com/paper/2203.07653/) (2022)
- [CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos](https://mlsanity.com/paper/2204.00716/) (2022)
- [Improving Biomedical Information Retrieval with Neural Retrievers](https://mlsanity.com/paper/2201.07745/) (2022)
- [Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection](https://mlsanity.com/paper/2109.10739/) (2021)
- [Boosted Dense Retriever](https://mlsanity.com/paper/2112.07771/) (2021)
- [Neural Retriever and Go Beyond: A Thesis Proposal](https://mlsanity.com/paper/2205.16005/) (2022)

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

- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications](https://mlsanity.com/paper/2409.09046/) (2024)
- [Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?](https://mlsanity.com/paper/2211.12707/) (2022)
- [Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis](https://mlsanity.com/paper/2504.05324/) (2025)
- [BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions](https://mlsanity.com/paper/2506.05766/) (2025)
- [Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings](https://mlsanity.com/paper/2506.08592/) (2025)
- [Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.30009/) (2026)

## Abstract (arXiv)

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance"? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves 13X memory while maintaining 98.0% performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.