Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the creativity of a piece of writing is challenging. Inspired by the Torrance Test of Creative Thinking (TTCT), which measures creativity as a process, we use the Consensual Assessment Technique [3] and propose the Torrance Test of Creative Writing (TTCW) to evaluate creativity as a product. TTCW consists of 14 binary tests organized into the original dimensions of Fluency, Flexibility, Originality, and Elaboration. We recruit 10 creative writers and implement a human assessment of 48 stories written either by professional authors or LLMs using TTCW. Our analysis shows that LLM-generated stories pass 3-10X less TTCW tests than stories written by professionals. In addition, we explore the use of LLMs as assessors to automate the TTCW evaluation, revealing that none of the LLMs positively correlate with the expert assessments.

The main concern of this study is to find the optimal design of truss structures considering sizing and layout variables simultaneously. As compared to purely sizing optimization problems, this problem is more challenging since the two types of variables involved are fundamentally different in nature. In this paper, a reinforcement learning method combining the update process and Monte Carlo tree search called the update Monte Carlo tree search (UMCTS) for sizing optimization problems is applied to solve combined sizing and layout optimization for truss structures. This study proposes a novel update process for nodal coordinates with two features. (1) The allowed range of each coordinate varies in each round. (2) Accelerators for the number of entries in the allowed range and iteration numbers are introduced to reduce the computation time. Furthermore, nodal coordinates and member areas are determined at the same time with only one search tree in each round. The validation and efficiency of the UMCTS are tested on benchmark problems of planar and spatial trusses with discrete sizing variables and continuous layout variables. It is shown that the CPU time of the UMCTS is two times faster than the branch and bound method. The numerical results demonstrate that the proposed method stably achieves a better solution than other traditional methods.

Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address the aforementioned ASR challenge, focusing on the Tunisian dialect. First, textual and audio data is collected and in some cases annotated. Second, we explore self-supervision, semi-supervision and few-shot code-switching approaches to push the state-of-the-art on different Tunisian test sets; covering different acoustic, linguistic and prosodic conditions. Finally, and given the absence of conventional spelling, we produce a human evaluation of our transcripts to avoid the noise coming from spelling inadequacies in our testing references. Our models, allowing to transcribe audio samples in a linguistic mix involving Tunisian Arabic, English and French, and all the data used during training and testing are released for public use and further improvements.

Training large language models to follow instructions makes them perform better on a wide range of tasks, generally becoming more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily generate harmful content. In this paper, we raise concerns over the safety of models that only emphasize helpfulness, not safety, in their instruction-tuning. We show that several popular instruction-tuned models are highly unsafe. Moreover, we show that adding just 3% safety examples (a few hundred demonstrations) in the training set when fine-tuning a model like LLaMA can substantially improve their safety. Our safety-tuning does not make models significantly less capable or helpful as measured by standard benchmarks. However, we do find a behavior of exaggerated safety, where too much safety-tuning makes models refuse to respond to reasonable prompts that superficially resemble unsafe ones. Our study sheds light on trade-offs in training LLMs to follow instructions and exhibit safe behavior.

We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions - an especially challenging task when prompts feature imaginary elements and artistic styles, given the complexity of interpreting the semantics and motions of these images. We focus on cinemagraphs of fluid elements, such as flowing rivers, and drifting clouds, which exhibit continuous motion and repetitive textures. Existing single-image animation methods fall short on artistic inputs, and recent text-based video methods frequently introduce temporal inconsistencies, struggling to keep certain regions static. To address these challenges, we propose an idea of synthesizing image twins from a single text prompt - a pair of an artistic image and its pixel-aligned corresponding natural-looking twin. While the artistic image depicts the style and appearance detailed in our text prompt, the realistic counterpart greatly simplifies layout and motion analysis. Leveraging existing natural image and video datasets, we can accurately segment the realistic image and predict plausible motion given the semantic information. The predicted motion can then be transferred to the artistic image to create the final cinemagraph. Our method outperforms existing approaches in creating cinemagraphs for natural landscapes as well as artistic and other-worldly scenes, as validated by automated metrics and user studies. Finally, we demonstrate two extensions: animating existing paintings and controlling motion directions using text.

Pre-training on large models is prevalent and emerging Fundamentally, a common goal of data mining applications with the ever-growing user-generated content in many using user-content interactions is to understand machine learning application categories. It has been user's behaviors [17] and content's properties. Researchers recognized that learning contextual knowledge from attempt multiple ways to model such behaviors: the datasets depicting user-content interaction plays The time-related nature of the interactions is a fit for a vital role in downstream tasks. Despite several sequential models, such as recurrent neural networks studies attempting to learn contextual knowledge via pretraining (RNN), and the interactions and relations can be modeled methods, finding an optimal training objective as graph neural networks (GNN). Conventionally, and strategy for this type of task remains a challenging the training objective is to minimize the loss of a specific problem. In this work, we contend that there are two task such that one model is tailored to a particular distinct aspects of contextual knowledge, namely the application (e.g., recommendation). This approach is user-side and the content-side, for datasets where usercontent simple and effective for every data mining application.

We investigate how robotic camera systems can offer new capabilities to computer-supported cooperative work through the design, development, and evaluation of a prototype system called Periscope. With Periscope, a local worker completes manipulation tasks with guidance from a remote helper who observes the workspace through a camera mounted on a semi-autonomous robotic arm that is co-located with the worker. Our key insight is that the helper, the worker, and the robot should all share responsibility of the camera view--an approach we call shared camera control. Using this approach, we present a set of modes that distribute the control of the camera between the human collaborators and the autonomous robot depending on task needs. We demonstrate the system's utility and the promise of shared camera control through a preliminary study where 12 dyads collaboratively worked on assembly tasks. Finally, we discuss design and research implications of our work for future robotic camera systems that facilitate remote collaboration.

The spread of misinformation, propaganda, and flawed argumentation has been amplified in the Internet era. Given the volume of data and the subtlety of identifying violations of argumentation norms, supporting information analytics tasks, like content moderation, with trustworthy methods that can identify logical fallacies is essential. In this paper, we formalize prior theoretical work on logical fallacies into a comprehensive three-stage evaluation framework of detection, coarse-grained, and fine-grained classification. We adapt existing evaluation datasets for each stage of the evaluation. We employ three families of robust and explainable methods based on prototype reasoning, instance-based reasoning, and knowledge injection. The methods combine language models with background knowledge and explainable mechanisms. Moreover, we address data sparsity with strategies for data augmentation and curriculum learning. Our three-stage framework natively consolidates prior datasets and methods from existing tasks, like propaganda detection, serving as an overarching evaluation testbed. We extensively evaluate these methods on our datasets, focusing on their robustness and explainability. Our results provide insight into the strengths and weaknesses of the methods on different components and fallacy classes, indicating that fallacy identification is a challenging task that may require specialized forms of reasoning to capture various classes. We share our open-source code and data on GitHub to support further work on logical fallacy identification.

CyberGuy breaks down how to share your WiFi password with other Android users. Many people are already using tools like OpenAI's ChatGPT generative AI chatbot and Bing, which also sources current information on the internet in its results, to help with various tasks, such as writing essays, creating images and more. Google is not far behind and has recently announced new generative AI experiences in Google Workspace that will allow you to create content with the help of AI. CLICK TO GET KURT'S FREE CYBERGUY NEWSLETTER WITH SECURITY ALERTS, QUICK TIPS, TECH REVIEWS AND EASY HOW-TO'S TO MAKE YOU SMARTER Google Duet AI is a new feature that can assist in answering emails. Google Duet AI is a new feature to help answer emails in Gmail, create images from texts, and proofread documents in Google Docs, to name a few skills.

Machine Learning models are being utilized extensively to drive recommender systems, which is a widely explored topic today. This is especially true of the music industry, where we are witnessing a surge in growth. Besides a large chunk of active users, these systems are fueled by massive amounts of data. These large-scale systems yield applications that aim to provide a better user experience and to keep customers actively engaged. In this paper, a distributed Machine Learning (ML) pipeline is delineated, which is capable of taking a subset of songs as input and producing a new subset of songs identified as being similar to the inputted subset. The publicly accessible Million Songs Dataset (MSD) enables researchers to develop and explore reasonably efficient systems for audio track analysis and recommendations, without having to access a commercialized music platform. The objective of the proposed application is to leverage an ML system trained to optimally recommend songs that a user might like.