Large Language Models (LLMs), with gradually improving reading comprehension and reasoning capabilities, are being applied to a range of complex language tasks, including the automatic generation of language data for various purposes. However, research on applying LLMs for automatic data generation in low-resource languages like Vietnamese is still underdeveloped and lacks comprehensive evaluation. In this paper, we explore the use of LLMs for automatic data generation for the Vietnamese fact-checking task, which faces significant data limitations. Specifically, we focus on fact-checking data where claims are synthesized from multiple evidence sentences to assess the information synthesis capabilities of LLMs. We develop an automatic data construction process using simple prompt techniques on LLMs and explore several methods to improve the quality of the generated data. To evaluate the quality of the data generated by LLMs, we conduct both manual quality assessments and performance evaluations using language models. Experimental results and manual evaluations illustrate that while the quality of the generated data has significantly improved through fine-tuning techniques, LLMs still cannot match the data quality produced by humans.

Dictionary learning (Rubinstein require capturing complex relations between et al., 2010) is a representation learning framework variables. We define a novel Graph-which aims to recover a finite set of atoms, called a Dictionary signal model, where a finite set dictionary, that can encode data through sparse coefficients. of graphs characterizes relationships in data On the other hand, graphs provide a natural distribution through a weighted sum of their representation of structured data with pairwise relationships, Laplacians. We propose a framework to infer described by edges between nodes. However, the graph dictionary representation from these relationships are often hidden, and we must infer observed data, along with a bilinear generalization them from data. of the primal-dual splitting algorithm to solve the learning problem. Our new formulation In this work, we introduce a novel Graph-Dictionary allows to include a priori knowledge signal model, GraphDict in short, to jointly address the on signal properties, as well as on underlying representation and the structure learning problems.

Generating accurate and consistent visual aids is a critical challenge in mathematics education, where visual representations like geometric shapes and functions play a pivotal role in enhancing student comprehension. This paper introduces a novel multi-agent framework that leverages Large Language Models (LLMs) to automate the creation of complex mathematical visualizations alongside coherent problem text. Our approach not only simplifies the generation of precise visual aids but also aligns these aids with the problem's core mathematical concepts, improving both problem creation and assessment. By integrating multiple agents, each responsible for distinct tasks such as numeric calculation, geometry validation, and visualization, our system delivers mathematically accurate and contextually relevant problems with visual aids. Evaluation across Geometry and Function problem types shows that our method significantly outperforms basic LLMs in terms of text coherence, consistency, relevance and similarity, while maintaining the essential geometrical and functional integrity of the original problems. Although some challenges remain in ensuring consistent visual outputs, our framework demonstrates the immense potential of LLMs in transforming the way educators generate and utilize visual aids in math education.

The growth of digital documents presents significant challenges in efficient management and knowledge extraction. Traditional methods often struggle with complex documents, leading to issues such as hallucinations and high latency in responses from Large Language Models (LLMs). ZeroG, an innovative approach, significantly mitigates these challenges by leveraging knowledge distillation and prompt tuning to enhance model performance. ZeroG utilizes a smaller model that replicates the behavior of a larger teacher model, ensuring contextually relevant and grounded responses, by employing a black-box distillation approach, it creates a distilled dataset without relying on intermediate features, optimizing computational efficiency. This method significantly enhances accuracy and reduces response times, providing a balanced solution for modern document management. Incorporating advanced techniques for document ingestion and metadata utilization, ZeroG improves the accuracy of question-and-answer systems. The integration of graph databases and robust metadata management further streamlines information retrieval, allowing for precise and context-aware responses. By transforming how organizations interact with complex data, ZeroG enhances productivity and user experience, offering a scalable solution for the growing demands of digital document management.

Upon release, ChatGPT3.5 shocked the software engineering community by its ability to generate answers to specialized questions about coding. Immediately, many educators wondered if it was possible to use the chatbot as a support tool that helps students answer their programming questions. This article evaluates this possibility at three levels: fundamental Computer Science knowledge (basic algorithms and data structures), core competency (design patterns), and advanced knowledge (quantum computing). In each case, we ask normalized questions several times to ChatGPT3.5, then look at the correctness of answers, and finally check if this creates issues. The main result is that the performances of ChatGPT3.5 degrades drastically as the specialization of the domain increases: for basic algorithms it returns answers that are almost always correct, for design patterns the generated code contains many code smells and is generally of low quality, but it is still sometimes able to fix it (if asked), and for quantum computing it is often blatantly wrong.

The topics of Artificial intelligence (AI) and especially Machine Learning (ML) are increasingly making their way into educational curricula. To facilitate the access for students, a variety of platforms, visual tools, and digital games are already being used to introduce ML concepts and strengthen the understanding of how AI works. We take a look at didactic principles that are employed for teaching computer science, define criteria, and, based on those, evaluate a selection of prominent existing platforms, tools, and games. Additionally, we criticize the approach of portraying ML mostly as a black-box and the resulting missing focus on creating an understanding of data, algorithms, and models that come with it. To tackle this issue, we present a concept that covers intermodal transfer, computational and explanatory thinking, ICE-T, as an extension of known didactic principles. With our multi-faceted concept, we believe that planners of learning units, creators of learning platforms and educators can improve on teaching ML.

Immense effort has been dedicated to minimizing the presence of harmful or biased generative content and better aligning AI output to human intention; however, research investigating the cultural values of LLMs is still in very early stages. Cultural values underpin how societies operate, providing profound insights into the norms, priorities, and decision making of their members. In recognition of this need for further research, we draw upon cultural psychology theory and the empirically-validated GLOBE framework to propose the LLM-GLOBE benchmark for evaluating the cultural value systems of LLMs, and we then leverage the benchmark to compare the values of Chinese and US LLMs. Our methodology includes a novel "LLMs-as-a-Jury" pipeline which automates the evaluation of open-ended content to enable large-scale analysis at a conceptual level. Results clarify similarities and differences that exist between Eastern and Western cultural value systems and suggest that open-generation tasks represent a more promising direction for evaluation of cultural values. We interpret the implications of this research for subsequent model development, evaluation, and deployment efforts as they relate to LLMs, AI cultural alignment more broadly, and the influence of AI cultural value systems on human-AI collaboration outcomes.

To What Extent Does the Perceived Obesity Level of Humanoid Robots Affect People's Trust in Them? Abstract-- Despite obesity being widely discussed in the social sciences, the effect of a robot's perceived obesity level on trust is not covered by the field of HRI. While in research regarding humans, Body Mass Index (BMI) is commonly used as an indicator of obesity, this scale is completely irrelevant in the context of robots, so it is challenging to operationalize the perceived obesity level of robots; indeed, while the effect of robot's size (or height) on people's trust in it was addressed in previous HRI papers, the perceived obesity level factor has not been addressed. This work examines to what extent the perceived obesity level of humanoid robots affects people's trust in them. To test this hypothesis, we conducted a within-subjects study where, using an online pre-validated questionnaire, the subjects were asked questions while being presented with two pictures of humanoids, one with a regular obesity level and the other with a high obesity level. The results show that humanoid robots with lower perceived obesity levels are significantly more likely to be trusted.

Deaf and hard-of-hearing (DHH) students face significant barriers in accessing science, technology, engineering, and mathematics (STEM) education, notably due to the scarcity of STEM resources in signed languages. To help address this, we introduce ASL STEM Wiki: a parallel corpus of 254 Wikipedia articles on STEM topics in English, interpreted into over 300 hours of American Sign Language (ASL). ASL STEM Wiki is the first continuous signing dataset focused on STEM, facilitating the development of AI resources for STEM education in ASL. We identify several use cases of ASL STEM Wiki with human-centered applications. Figure 1: One use case of ASL STEM Wiki is automatic For example, because this dataset sign suggestion. Given an English sentence and a video highlights the frequent use of fingerspelling for of its ASL interpretation, the model detects all clips of technical concepts, which inhibits DHH students' ASL that contains fingerspelling (FS). Then, given the ability to learn, we develop models to detected FS clip and the English sentence, the model identify fingerspelled words--which can later identifies which English phrase in the sentence is fingerspelled be used to query for appropriate ASL signs to in the clip. The English phrase can be used to suggest to interpreters.

Differential privacy (DP) is a formal notion that restricts the privacy leakage of an algorithm when running on sensitive data, in which privacy-utility trade-off is one of the central problems in private data analysis. In this work, we investigate the fundamental limits of differential privacy in online learning algorithms and present evidence that separates three types of constraints: no DP, pure DP, and approximate DP. We first describe a hypothesis class that is online learnable under approximate DP but not online learnable under pure DP under the adaptive adversarial setting. This indicates that approximate DP must be adopted when dealing with adaptive adversaries. We then prove that any private online learner must make an infinite number of mistakes for almost all hypothesis classes. This essentially generalizes previous results and shows a strong separation between private and non-private settings since a finite mistake bound is always attainable (as long as the class is online learnable) when there is no privacy requirement.