# Investigating Mixture of Experts in Dense Retrieval

arXiv: https://arxiv.org/abs/2412.11864 · HTML: https://mlsanity.com/paper/2412.11864/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning](https://mlsanity.com/paper/2210.17451/) (2022)
- [Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models](https://mlsanity.com/paper/2305.14705/) (2023)
- [Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers](https://mlsanity.com/paper/2303.01610/) (2023)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning](https://mlsanity.com/paper/2210.15212/) (2022)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval](https://mlsanity.com/paper/2304.10195/) (2023)
- [DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts](https://mlsanity.com/paper/2403.13468/) (2024)
- [Mixture of Experts for Biomedical Question Answering](https://mlsanity.com/paper/2204.07469/) (2022)
- [CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval](https://mlsanity.com/paper/2311.02834/) (2023)

## Built on by (most cited first, 4 of 4)

- [LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints](https://mlsanity.com/paper/2510.27054/) (2025)
- [Mixture of Experts Approaches in Dense Retrieval Tasks](https://mlsanity.com/paper/2510.15683/) (2025)
- [Research on Violent Text Detection System Based on BERT-fasttext Model](https://mlsanity.com/paper/2412.16455/) (2024)
- [Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees](https://mlsanity.com/paper/2607.14157/) (2026)

## Abstract (arXiv)

While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE) architecture. While previous IR studies have incorporated MoE architectures within the Transformer layers of DRMs, our work investigates an architecture that integrates a single MoE block (SB-MoE) after the output of the final Transformer layer. Our empirical evaluation investigates how SB-MoE compares, in terms of retrieval effectiveness, to standard fine-tuning. In detail, we fine-tune three DRMs (TinyBERT, BERT, and Contriever) across four benchmark collections with and without adding the MoE block. Moreover, since MoE showcases performance variations with respect to its parameters (i.e., the number of experts), we conduct additional experiments to investigate this aspect further. The findings show the effectiveness of SB-MoE especially for DRMs with a low number of parameters (i.e., TinyBERT), as it consistently outperforms the fine-tuned underlying model on all four benchmarks. For DRMs with a higher number of parameters (i.e., BERT and Contriever), SB-MoE requires larger numbers of training samples to yield better retrieval performance.