相关论文: PMANet: Malicious URL detection via post-trained l…

We address the challenging task of cross-modal moment retrieval, which aims to localize a temporal segment from an untrimmed video described by a natural language query. It poses great challenges over the proper semantic alignment between…

Recent pre-trained language models (PLMs) achieved great success on many natural language processing tasks through learning linguistic features and contextualized sentence representation. Since attributes captured in stacked layers of PLMs…

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the…

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over…

Motivated by the success of pre-trained language models such as BERT in a broad range of natural language processing (NLP) tasks, recent research efforts have been made for adapting these models for different application domains. Along this…

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and…

Phishing is considered to be one of the most prevalent cyber-attacks because of its immense flexibility and alarmingly high success rate. Even with adequate training and high situational awareness, it can still be hard for users to…

The massive spread of hate speech, hateful content targeted at specific subpopulations, is a problem of critical social importance. Automated methods of hate speech detection typically employ state-of-the-art deep learning (DL)-based text…

Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have…

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…

Trusting the accuracy of data inputted on online platforms can be difficult due to the possibility of malicious websites gathering information for unlawful reasons. Analyzing each website individually becomes challenging with the presence…

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Phishing is the most prevalent type of cyber-attack today and is recognized as the leading source of data breaches with significant consequences for both individuals and corporations. Web-based phishing attacks are the most frequent with…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…