# Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings

arXiv: https://arxiv.org/abs/2205.02303 · HTML: https://mlsanity.com/paper/2205.02303/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2022.

## Built on by (most cited first, 23 of 23)

- [REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://mlsanity.com/paper/2502.12342/) (2025)
- [MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System](https://mlsanity.com/paper/2503.09600/) (2025)
- [Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception](https://mlsanity.com/paper/2410.12788/) (2024)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval](https://mlsanity.com/paper/2504.17884/) (2025)
- [Investigating the Robustness of Retrieval-Augmented Generation at the Query Level](https://mlsanity.com/paper/2507.06956/) (2025)
- [A Study on FGSM Adversarial Training for Neural Retrieval](https://mlsanity.com/paper/2301.10576/) (2023)
- [On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective](https://mlsanity.com/paper/2306.12756/) (2023)
- [On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering](https://mlsanity.com/paper/2209.12944/) (2022)
- [Typo-Robust Representation Learning for Dense Retrieval](https://mlsanity.com/paper/2306.10348/) (2023)
- [Noise-Robust Dense Retrieval via Contrastive Alignment Post Training](https://mlsanity.com/paper/2304.03401/) (2023)
- [Benchmark Granularity and Model Robustness for Image-Text Retrieval](https://mlsanity.com/paper/2407.15239/) (2024)
- [Investigating Mixture of Experts in Dense Retrieval](https://mlsanity.com/paper/2412.11864/) (2024)
- [Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection](https://mlsanity.com/paper/2307.16816/) (2023)
- [Misspellings in Natural Language Processing: A survey](https://mlsanity.com/paper/2501.16836/) (2025)
- [How You Ask Matters! Adaptive RAG Robustness to Query Variations](https://mlsanity.com/paper/2604.10745/) (2026)
- [LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias](https://mlsanity.com/paper/2307.02912/) (2023)
- [A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering](https://mlsanity.com/paper/2409.13483/) (2024)
- [Mixture of Experts Approaches in Dense Retrieval Tasks](https://mlsanity.com/paper/2510.15683/) (2025)
- [On Monotonic Aggregation for Open-domain QA](https://mlsanity.com/paper/2308.04176/) (2023)
- [Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents](https://mlsanity.com/paper/2603.24556/) (2026)
- [On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability](https://mlsanity.com/paper/2604.16576/) (2026)
- [Retrieval Sensitivity to Identity Signals in Queries](https://mlsanity.com/paper/2609.36534/) (2026)

## Abstract (arXiv)

Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense retrieval models are evaluated on clean and curated datasets. However, when deployed in real-life applications, these models encounter noisy user-generated text. That said, the performance of state-of-the-art dense retrievers can substantially deteriorate when exposed to noisy text. In this work, we study the robustness of dense retrievers against typos in the user question. We observe a significant drop in the performance of the dual-encoder model when encountering typos and explore ways to improve its robustness by combining data augmentation with contrastive learning. Our experiments on two large-scale passage ranking and open-domain question answering datasets show that our proposed approach outperforms competing approaches. Additionally, we perform a thorough analysis on robustness. Finally, we provide insights on how different typos affect the robustness of embeddings differently and how our method alleviates the effect of some typos but not of others.