# Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval

arXiv: https://arxiv.org/abs/2604.03403 · HTML: https://mlsanity.com/paper/2604.03403/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://mlsanity.com/paper/2403.15246/) (2024)
- [MAIR: A Massive Benchmark for Evaluating Instructed Retrieval](https://mlsanity.com/paper/2410.10127/) (2024)
- [Transferring Linear Features Across Language Models With Model Stitching](https://mlsanity.com/paper/2506.06609/) (2025)
- [Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k](https://mlsanity.com/paper/2506.08479/) (2025)
- [Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models](https://mlsanity.com/paper/2402.13492/) (2024)
- [Search-Adaptor: Embedding Customization for Information Retrieval](https://mlsanity.com/paper/2310.08750/) (2023)
- [Syntriever: How to Train Your Retriever with Synthetic Data from LLMs](https://mlsanity.com/paper/2502.03824/) (2025)
- [Reproducing NevIR: Negation in Neural Information Retrieval](https://mlsanity.com/paper/2502.13506/) (2025)
- [Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking](https://mlsanity.com/paper/2405.07920/) (2024)
- [Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases](https://mlsanity.com/paper/2509.23471/) (2025)

## Built on by (most cited first, 2 of 2)

- [When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections](https://mlsanity.com/paper/2609.32488/) (2026)
- [Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence](https://mlsanity.com/paper/2610.13277/) (2026)

## Abstract (arXiv)

Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collections. While stronger embedders can better understand such queries, re-embedding large corpora or fine-tuning large models is often impractical. We propose Efficient Retrieval Adapter (ERA), a query-side adapter learning framework for re-index-free retrieval adaptation. ERA first aligns the embedding spaces of a strong query embedder and a lightweight document embedder using unlabeled corpus documents, and then adapts the aligned query representation with a small number of labeled query-document pairs. Across 126 MAIR retrieval tasks from six domains, ERA improves average nDCG@10 by up to 8.2 points in symmetric settings and by more than 12 points in asymmetric settings, while using substantially fewer labels than supervised adapter training. These results show that retrieval systems can benefit from stronger query understanding without updating backbone embedders or rebuilding document indexes.