Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical problem of epistemic miscalibration -- where a model's linguistic assertiveness fails to reflect its true internal certainty. We introduce a new human-labeled dataset and a novel method for measuring the linguistic assertiveness of Large Language Models (LLMs) which cuts error rates by over 50% relative to previous benchmarks. Validated across multiple datasets, our method reveals a stark misalignment between how confidently models linguistically present information and their actual accuracy. Further human evaluations confirm the severity of this miscalibration. This evidence underscores the urgent risk of the overstated certainty LLMs hold which may mislead users on a massive scale. Our framework provides a crucial step forward in diagnosing this miscalibration, offering a path towards correcting it and more trustworthy AI across domains. Large Language Models (LLMs) have markedly transformed how humans seek and consume information, becoming integral across diverse fields such as public health (Ali et al., 2023), coding (Zambrano et al., 2023), and education (Whalen & et al., 2023). Despite their growing influence, LLMs are not without shortcomings. One notable issue is the potential for generating responses that, while convincing, may be inaccurate or nonsensical--a long-standing phenomenon often referred to as "hallucinations" (Jo, 2023; Huang et al., 2023; Zhou et al., 2024b). This raises concerns about the reliability and trustworthiness of these models. A critical aspect of trustworthiness in LLMs is epistemic calibration, which represents the alignment between a model's internal confidence in its outputs and the way it expresses that confidence through natural language. Misalignment between internal certainty and external expression can lead to users being misled by overconfident or underconfident statements, posing significant risks in high-stakes domains such as legal advice, medical diagnosis, and misinformation detection. While of great normative concern, how LLMs express linguistic uncertainty has received relatively little attention to date (Sileo & Moens, 2023; Belem et al., 2024). Figures 1 and 5 illustrate the issue of epistemic calibration providing insights into the operation of certainty in the context of human interactions with LLMs. Distinct Roles of Certainty: Internal certainty and linguistic assertiveness have distinct functions within LLM interactions that shape individual beliefs. Human access to LLM certainty: Linguistic assertiveness holds a critical role as the primary form of certainty available to users.

Music is a potent form of expression that can communicate, accentuate or even create the emotions of an individual or a collective. Both historically and in contemporary experiences, musical expression was and is commonly instrumentalized for social, political and/or economic purposes. Generative artificial intelligence provides a wealth of both opportunities and challenges with regard to music and its role in society. This paper discusses a proposed project integrating artificial intelligence and popular music, with the ultimate goal of creating a powerful tool for implementing music for social transformation, education, healthcare, and emotional well-being. Given that it is being presented at the outset of a collaboration between a computer scientist/data analyst and an ethnomusicologist/social anthropologist. it is mainly conceptual and somewhat speculative in nature.

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks mainly rely on scenario camouflage, prompt obfuscation, prompt optimization, and prompt iterative optimization to conceal malicious prompts. In particular, sequential prompt chains in a single query can lead LLMs to focus on certain prompts while ignoring others, facilitating context manipulation. This paper introduces SequentialBreak, a novel jailbreak attack that exploits this vulnerability. We discuss several scenarios, not limited to examples like Question Bank, Dialog Completion, and Game Environment, where the harmful prompt is embedded within benign ones that can fool LLMs into generating harmful responses. The distinct narrative structures of these scenarios show that SequentialBreak is flexible enough to adapt to various prompt formats beyond those discussed. Extensive experiments demonstrate that SequentialBreak uses only a single query to achieve a substantial gain of attack success rate over existing baselines against both open-source and closed-source models. Through our research, we highlight the urgent need for more robust and resilient safeguards to enhance LLM security and prevent potential misuse. All the result files and website associated with this research are available in this GitHub repository: https://anonymous.4open.science/r/JailBreakAttack-4F3B/.

In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated by Latent Diffusion Models (LDM) by identifying artifacts introduced by their autoencoders. By training a detector to distinguish between real images and those reconstructed by the LDM autoencoder, the method enables detection of generated images without directly training on them. The novelty of this research lies in the fact that, unlike similar approaches, this method does not require training on synthesized data, significantly reducing computational costs and enhancing generalization ability. Experimental results show high detection accuracy with minimal false positives, making this approach a promising tool for combating fake images.

To effectively manage and utilize knowledge graphs, it is crucial to have metrics that can assess the quality of knowledge graphs from various perspectives. While there have been studies on knowledge graph quality metrics, there has been a lack of research on metrics that measure how richly ontologies, which form the backbone of knowledge graphs, are defined or the impact of richly defined ontologies. In this study, we propose a new metric called Class Granularity, which measures how well a knowledge graph is structured in terms of how finely classes with unique characteristics are defined. Furthermore, this research presents potential impact of Class Granularity in knowledge graph's on downstream tasks. In particular, we explore its influence on graph embedding and provide experimental results. Additionally, this research goes beyond traditional Linked Open Data comparison studies, which mainly focus on factors like scale and class distribution, by using Class Granularity to compare four different LOD sources.

Musicians frequently use social media to express their opinions, but they often convey different messages in their music compared to their posts online. Some utilize these platforms to abuse their colleagues, while others use it to show support for political candidates or engage in activism, as seen during the #EndSars protest. There are extensive research done on offensive language detection on social media, the usage of offensive language by musicians has received limited attention. In this study, we introduce VocalTweets, a code-switched and multilingual dataset comprising tweets from 12 prominent Nigerian musicians, labeled with a binary classification method as Normal or Offensive. We trained a model using HuggingFace's base-Twitter-RoBERTa, achieving an F1 score of 74.5. Additionally, we conducted cross-corpus experiments with the OLID dataset to evaluate the generalizability of our dataset.

My eye was caught by a striking photograph in the most recent edition of Charles Arthur's Substack newsletter Social Warming. It shows a narrow street in the aftermath of the "rain bomb" that devastated the region of Valencia in Spain. A year's worth of rain fell in a single day, and in some towns more than 490 litres a square metre fell in eight hours. Water is very heavy, so if there's a gradient it will flow downhill with the kind of force that can pick up a heavy SUV and toss it around like a toy. And if it channels down a narrow urban street, it will throw parked cars around like King Kong in a bad mood.

Ofcom has warned tech firms that content from chatbots impersonating real and fictional people could fall foul of the UK's new digital laws. The communications regulator issued the guidance after it emerged that users on the Character.AI platform had created avatars mimicking the deceased British teenagers Brianna Ghey and Molly Russell. Under pressure from digital safety campaigners to clarify the situation, Ofcom underlined that content created by user-made chatbots would come under the scope of the Online Safety Act. Without naming the US-based artificial intelligence firm Character.AI, Ofcom said a site or app that allowed users to create their own chatbots for other people to interact with would be covered by the act. "This includes services that provide tools for users to create chatbots that mimic the personas of real and fictional people, which can be submitted to a chatbot library for others to interact with," said Ofcom. In an open letter, Ofcom also said any user-to-user site or app – such as a social media platform or messaging app – that enabled people to share content generated by a chatbot on that site with others would also be in scope.

Although misinformation tends to spread online, it can have serious real-world consequences. In order to develop automated tools to detect and mitigate the impact of misinformation, researchers must leverage algorithms that can adapt to the modality (text, images and video), the source, and the content of the false information. However, these characteristics tend to change dynamically across time, making it challenging to develop robust algorithms to fight misinformation spread. Therefore, this paper uses natural language processing to find common characteristics of political misinformation over a twelve year period. The results show that misinformation has increased dramatically in recent years and that it has increasingly started to be shared from sources with primary information modalities of text and images (e.g., Facebook and Instagram), although video sharing sources containing misinformation are starting to increase (e.g., TikTok). Moreover, it was discovered that statements expressing misinformation contain more negative sentiment than accurate information. However, the sentiment associated with both accurate and inaccurate information has trended downward, indicating a generally more negative tone in political statements across time. Finally, recurring misinformation categories were uncovered that occur over multiple years, which may imply that people tend to share inaccurate statements around information they fear or don't understand (Science and Medicine, Crime, Religion), impacts them directly (Policy, Election Integrity, Economic) or Public Figures who are salient in their daily lives. Together, it is hoped that these insights will assist researchers in developing algorithms that are temporally invariant and capable of detecting and mitigating misinformation across time.

Teasers are an effective tool for promoting content in entertainment, commercial and educational fields. However, creating an effective teaser for long videos is challenging for it requires long-range multimodal modeling on the input videos, while necessitating maintaining audiovisual alignments, managing scene changes and preserving factual accuracy for the output teasers. Due to the lack of a publicly-available dataset, progress along this research direction has been hindered. In this work, we present DocumentaryNet, a collection of 1,269 documentaries paired with their teasers, featuring multimodal data streams of video, speech, music, sound effects and narrations. With DocumentaryNet, we propose a new two-stage system for generating teasers from long documentaries. The proposed TeaserGen system first generates the teaser narration from the transcribed narration of the documentary using a pretrained large language model, and then selects the most relevant visual content to accompany the generated narration through language-vision models. For narration-video matching, we explore two approaches: a pretraining-based model using pretrained contrastive language-vision models and a deep sequential model that learns the mapping between the narrations and visuals. Our experimental results show that the pretraining-based approach is more effective at identifying relevant visual content than directly trained deep autoregressive models.