# RouterRetriever: Routing over a Mixture of Expert Embedding Models

arXiv: https://arxiv.org/abs/2409.02685 · HTML: https://mlsanity.com/paper/2409.02685/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Condenser: a Pre-training Architecture for Dense Retrieval](https://mlsanity.com/paper/2104.08253/) (2021)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval](https://mlsanity.com/paper/2302.07452/) (2023)
- [Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM](https://mlsanity.com/paper/2403.07816/) (2024)
- [Exploring the Benefits of Training Expert Language Models over Instruction Tuning](https://mlsanity.com/paper/2302.03202/) (2023)
- [FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://mlsanity.com/paper/2403.15246/) (2024)
- [Learning to Route Among Specialized Experts for Zero-Shot Generalization](https://mlsanity.com/paper/2402.05859/) (2024)
- [Learning to Decode Collaboratively with Multiple Language Models](https://mlsanity.com/paper/2403.03870/) (2024)
- [Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models](https://mlsanity.com/paper/2305.09955/) (2023)
- [INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models](https://mlsanity.com/paper/2402.14334/) (2024)
- [Decomposing Complex Queries for Tip-of-the-tongue Retrieval](https://mlsanity.com/paper/2305.15053/) (2023)
- [Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization](https://mlsanity.com/paper/2311.10847/) (2023)
- [Systematic Evaluation of Neural Retrieval Models on the Touch'e 2020 Argument Retrieval Subset of BEIR](https://mlsanity.com/paper/2407.07790/) (2024)

## Built on by (most cited first, 12 of 12)

- [FlexOlmo: Open Language Models for Flexible Data Use](https://mlsanity.com/paper/2507.07024/) (2025)
- [Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval](https://mlsanity.com/paper/2511.02770/) (2025)
- [LTRR: Learning To Rank Retrievers for LLMs](https://mlsanity.com/paper/2506.13743/) (2025)
- [Guarded Query Routing for Large Language Models](https://mlsanity.com/paper/2505.14524/) (2025)
- [IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering](https://mlsanity.com/paper/2602.17687/) (2026)
- [Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval](https://mlsanity.com/paper/2511.13293/) (2025)
- [R3AG: Retriever Routing for Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.22849/) (2026)
- [Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts](https://mlsanity.com/paper/2606.14929/) (2026)
- [MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning](https://mlsanity.com/paper/2510.21093/) (2025)
- [KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning](https://mlsanity.com/paper/2606.00532/) (2026)
- [Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees](https://mlsanity.com/paper/2607.14157/) (2026)
- [Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers](https://mlsanity.com/paper/2609.13486/) (2026)

## Abstract (arXiv)

Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often underperform models trained on domain-specific data when testing on their respective domains. Prior work in information retrieval has tackled this through multi-task training, but the idea of routing over a mixture of domain-specific expert retrievers remains unexplored despite the popularity of such ideas in language model generation research. In this work, we introduce RouterRetriever, a retrieval model that leverages a mixture of domain-specific experts by using a routing mechanism to select the most appropriate expert for each query. RouterRetriever is lightweight and allows easy addition or removal of experts without additional training. Evaluation on the BEIR benchmark demonstrates that RouterRetriever outperforms both models trained on MSMARCO (+2.1 absolute nDCG@10) and multi-task models (+3.2). This is achieved by employing our routing mechanism, which surpasses other routing techniques (+1.8 on average) commonly used in language modeling. Furthermore, the benefit generalizes well to other datasets, even in the absence of a specific expert on the dataset. RouterRetriever is the first work to demonstrate the advantages of routing over a mixture of domain-specific expert embedding models as an alternative to a single, general-purpose embedding model, especially when retrieving from diverse, specialized domains.