4 papers
ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving
Zain Ul Abedin, Shahzeb Qamar, Lucie Flek +1
While Large Language Models (LLMs) have shown impressive capabilities in math problem-solving tasks, their robustness to noisy inputs is not well-studied. We propose ArithmAttack t…
Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors
Pulkit Arora, Akbar Karimi, Lucie Flek
Despite their linguistic prowess, LLMs have been shown to be vulnerable to small input perturbations. While robustness to local adversarial changes has been studied, robustness to…
Exploring Robustness of Multilingual LLMs on Real-World Noisy Data
Amirhossein Aliakbarzadeh, Lucie Flek, Akbar Karimi
Large Language Models (LLMs) are trained on Web data that might contain spelling errors made by humans. But do they become robust to similar real-world noise? In this paper, we inv…
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
Timo Saala, Lucie Flek, Alexander Jung +5
Correlations between input parameters play a crucial role in many scientific classification tasks, since these are often related to fundamental laws of nature. For example, in high…