相关论文: OpenFact at CheckThat! 2024: Combining Multiple At…

Pre-trained language model word representation, such as BERT, have been extremely successful in several Natural Language Processing tasks significantly improving on the state-of-the-art. This can largely be attributed to their ability to…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

This study addresses the critical challenges of assessing foundational academic skills by leveraging advancements in natural language processing (NLP). Traditional assessment methods often struggle to provide timely and comprehensive…

While current Automated Essay Scoring (AES) methods demonstrate high scoring agreement with human raters, their decision-making mechanisms are not fully understood. Our proposed method, using counterfactual intervention assisted by Large…

Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. Most…

Context: Software vulnerabilities pose a significant threat to modern software systems, as evidenced by the growing number of reported vulnerabilities and cyberattacks. These escalating trends underscore the urgent need for effective…

State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that can provably…

We describe the third edition of the CheckThat! Lab, which is part of the 2020 Cross-Language Evaluation Forum (CLEF). CheckThat! proposes four complementary tasks and a related task from previous lab editions, offered in English, Arabic,…

Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, which can effectively transfer between different models…

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

We present an overview of the third edition of the CheckThat! Lab at CLEF 2020. The lab featured five tasks in two different languages: English and Arabic. The first four tasks compose the full pipeline of claim verification in social…

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

With the freedom of communication provided in online social media, hate speech has increasingly generated. This leads to cyber conflicts affecting social life at the individual and national levels. As a result, hateful content…

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

Though model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied. In this paper, we conduct the first quantitative analysis on the robustness of pre-trained Seq2Seq…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…