mlsanityData to 7 Oct 2026

Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering

arXiv 2104.07646 ↗First posted 15 Apr 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent approaches have exploited weaknesses in monolingual question answering (QA) models by adding adversarial statements to the passage. These attacks caused a reduction in state-of-the-art performance by almost 50%. In this paper, we are the first to explore and successfully attack a multilingual QA (MLQA) system pre-trained on multilingual BERT using several attack strategies for the adversarial statement reducing performance by as much as 85%. We show that the model gives priority to English and the language of the question regardless of the other languages in the QA pair. Further, we also show that adding our attack strategies during training helps alleviate the attacks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

19 of 25 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  6. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  7. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
  8. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  9. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  10. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  11. 2017DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applicationscited by 110
  12. 2018DRCD: a Chinese Machine Reading Comprehension Datasetcited by 57
7 more
  1. 2019Neural Arabic Question Answeringcited by 48
  2. 2019Universal Dependency Parsing from Scratchcited by 46
  3. 2020What do Models Learn from Question Answering Datasets?cited by 45
  4. 2018Robust Machine Comprehension Models via Adversarial Trainingcited by 44
  5. 2018Multi-granularity hierarchical attention fusion networks for reading comprehension and question answeringcited by 28
  6. 2018Multilingual Extractive Reading Comprehension by Runtime Machine Translationcited by 17
  7. 2020Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehensioncited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 3.

6 papers.

  1. 2024Authorship Obfuscation in Multilingual Machine-Generated Text Detectioncited by 19
  2. 2022There is more than one kind of robustness: Fooling Whisper with adversarial examplescited by 11
  3. 2022A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deceptioncited by 1
  4. 2023From text to multimodal: a survey of adversarial example generation in question answering systemscited by 0
  5. 2024A Generative Adversarial Attack for Multilingual Text Classifierscited by 0
  6. 2024Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approachcited by 0