mlsanityData to 14 Oct 2026

Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages

arXiv 2412.10805 ↗First posted 14 Dec 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Pre-trained language models (PLMs) are known to be susceptible to perturbations to the input text, but existing works do not explicitly focus on linguistically grounded attacks, which are subtle and more prevalent in nature. In this paper, we study whether PLMs are agnostic to linguistically grounded attacks or not. To this end, we offer the first study addressing this, investigating different Indic languages and various downstream tasks. Our findings reveal that although PLMs are susceptible to linguistic perturbations, when compared to non-linguistic attacks, PLMs exhibit a slightly lower susceptibility to linguistic attacks. This highlights that even constrained attacks are effective. Moreover, we investigate the implications of these outcomes across a range of languages, encompassing diverse language families and different scripts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 14 Dec 2024.

Builds on

26 of 57 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  7. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2016Adversarial Machine Learning at Scalecited by 936
  10. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  11. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  12. 2020Language-agnostic BERT Sentence Embeddingcited by 627
14 more
  1. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
  2. 2018Generating Natural Language Adversarial Examplescited by 424
  3. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
  4. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 345
  5. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  6. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 286
  7. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  8. 2021MuRIL: Multilingual Representations for Indian Languagescited by 179
  9. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 163
  10. 2022Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languagescited by 102
  11. 2019Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systemscited by 101
  12. 2020It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbationscited by 64
  13. 2022Robust Conversational Agents against Imperceptible Toxicity Triggerscited by 23
  14. 2022Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretrainingcited by 9

Built on by

Not cited yet.