# Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters

arXiv: https://arxiv.org/abs/2212.10448 · HTML: https://mlsanity.com/paper/2212.10448/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation](https://mlsanity.com/paper/2106.03164/) (2021)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Deeper Text Understanding for IR with Contextual Neural Language Modeling](https://mlsanity.com/paper/1905.09217/) (2019)
- [UNKs Everywhere: Adapting Multilingual Language Models to New Scripts](https://mlsanity.com/paper/2012.15562/) (2020)
- [Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models](https://mlsanity.com/paper/2201.08471/) (2022)
- [Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition](https://mlsanity.com/paper/2012.01687/) (2020)
- [On Cross-Lingual Retrieval with Multilingual Text Encoders](https://mlsanity.com/paper/2112.11031/) (2021)
- [MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale](https://mlsanity.com/paper/2010.00980/) (2020)
- [Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval](https://mlsanity.com/paper/2204.02292/) (2022)
- [Learning Cross-Lingual IR from an English Retriever](https://mlsanity.com/paper/2112.08185/) (2021)
- [C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval](https://mlsanity.com/paper/2204.11989/) (2022)
- [A Study of Neural Matching Models for Cross-lingual IR](https://mlsanity.com/paper/2005.12994/) (2020)
- [HC4: A New Suite of Test Collections for Ad Hoc CLIR](https://mlsanity.com/paper/2201.09992/) (2022)
- [Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2109.02789/) (2021)

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

- [Soft Prompt Decoding for Multilingual Dense Retrieval](https://mlsanity.com/paper/2305.09025/) (2023)
- [ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval](https://mlsanity.com/paper/2402.15059/) (2024)
- [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025)
- [Query-aware routing for Cross-lingual performance gains in Encoders](https://mlsanity.com/paper/2610.02875/) (2026)

## Abstract (arXiv)

A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This multilingual model is fined-tuned to the retrieval task with monolingual data such as English MS MARCO using the same training recipe as the monolingual retrieval model used. However, such transferred models suffer from mismatches in the languages of the input text during training and inference. In this work, we propose transferring monolingual retrieval models using adapters, a parameter-efficient component for a transformer network. By adding adapters pretrained on language tasks for a specific language with task-specific adapters, prior work has shown that the adapter-enhanced models perform better than fine-tuning the entire model when transferring across languages in various NLP tasks. By constructing dense retrieval models with adapters, we show that models trained with monolingual data are more effective than fine-tuning the entire model when transferring to a Cross Language Information Retrieval (CLIR) setting. However, we found that the prior suggestion of replacing the language adapters to match the target language at inference time is suboptimal for dense retrieval models. We provide an in-depth analysis of this discrepancy between other cross-language NLP tasks and CLIR.