# Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

arXiv: https://arxiv.org/abs/2506.07645 · HTML: https://mlsanity.com/paper/2506.07645/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [KLEJ: Comprehensive Benchmark for Polish Language Understanding](https://mlsanity.com/paper/2005.00630/) (2020)
- [HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish](https://mlsanity.com/paper/2105.01735/) (2021)
- [Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation](https://mlsanity.com/paper/2410.18565/) (2024)
- [This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish](https://mlsanity.com/paper/2211.13112/) (2022)
- [Assessing generalization capability of text ranking models in Polish](https://mlsanity.com/paper/2402.14318/) (2024)

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

- [PL-Guard: Benchmarking Language Model Safety for Polish](https://mlsanity.com/paper/2506.16322/) (2025)
- [LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2608.14626/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive capabilities across various natural language processing (NLP) tasks in recent years. However, their susceptibility to jailbreaks and perturbations necessitates additional evaluations. Many LLMs are multilingual, but safety-related training data contains mainly high-resource languages like English. This can leave them vulnerable to perturbations in low-resource languages such as Polish. We show how surprisingly strong attacks can be cheaply created by altering just a few characters and using a small proxy model for word importance calculation. We find that these character and word-level attacks drastically alter the predictions of different LLMs, suggesting a potential vulnerability that can be used to circumvent their internal safety mechanisms. We validate our attack construction methodology on Polish, a low-resource language, and find potential vulnerabilities of LLMs in this language. Additionally, we show how it can be extended to other languages. We release the created datasets and code for further research.