7 accepted papers
LLM-augmented online disinformation is of particular concern for low-resource languages, given their prior limited exposure to it. While current LLMs lack fluidity in such languages, their multilingual and emerging capabilities can potentially still be leveraged.In this paper, we investigate whether
Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related to various factors (e.g., data size, economic and social factors) whose impact, however, turns out to be inconsistent. In
We introduce BUST, a comprehensive benchmark designed to evaluate detectors of texts generated by instruction-tuned large language models (LLMs). Unlike previous benchmarks, our focus lies on evaluating the performance of detector systems, acknowledging the inevitable influence of the underlying tas…
Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new targeted adversarial attack against NMT models. In particular, our…
Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this pa-per, we propose a gradient-based adversarial attack against transformer-based text classifiers. The adversarial perturbation…
This paper deals with the problem of incre-mental dialect identification. Our goal is toreliably determine the dialect before the fullutterance is given as input. The major partof the previous research on dialect identification has been model-centric, focusing on performance. We address a new questi…
Explainability is a key requirement for text classification in many application domains ranging from sentiment analysis to medical diagnosis or legal reviews. Existing methods often rely on "attention" mechanisms for explaining classification results by estimating the relative importance of input un…