Related papers: Multimodal datasets: misogyny, pornography, and ma…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

How does the progressive embracement of Large Language Models (LLMs) affect scientific peer reviewing? This multifaceted question is fundamental to the effectiveness -- as well as to the integrity -- of the scientific process. Recent…

Existing methods for evaluating the harmfulness of content generated by large language models (LLMs) have been well studied. However, approaches tailored to multimodal large language models (MLLMs) remain underdeveloped and lack depth. This…

Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy,…

Deep learning-based methods have pushed the limits of the state-of-the-art in face analysis. However, despite their success, these models have raised concerns regarding their bias towards certain demographics. This bias is inflicted both by…

The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical…

Multimodal misinformation, such as miscaptioned images, where captions misrepresent an image's origin, context, or meaning, poses a growing challenge in the digital age. Due to the scarcity of large-scale annotated datasets for multimodal…

The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information,…

Mental health disorders are rising worldwide. However, the availability of trained clinicians has not scaled proportionally, leaving many people without adequate or timely support. To bridge this gap, recent studies have shown the promise…

Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…

Gender bias in artificial intelligence (AI) and natural language processing has garnered significant attention due to its potential impact on societal perceptions and biases. This research paper aims to analyze gender bias in Large Language…

While there have been significant gains in the field of automated video description, the generalization performance of automated description models to novel domains remains a major barrier to using these systems in the real world. Most…

The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI…

The importance of addressing fairness and bias in artificial intelligence (AI) systems cannot be over-emphasized. Mainstream media has been awashed with news of incidents around stereotypes and other types of bias in many of these systems…

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination…

Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the…

Online misinformation poses an escalating threat, amplified by the Internet's open nature and increasingly capable LLMs that generate persuasive yet deceptive content. Existing misinformation detection methods typically focus on either…

Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pose serious security issues. This paper systematizes our…

Recent advancements in Large Language Models (LLMs), such as ChatGPT and LLaMA, have significantly transformed Natural Language Processing (NLP) with their outstanding abilities in text generation, summarization, and classification.…