Document understanding (DU) focuses on the automatic interpretation and processing of documents, encompassing complex layout structures and multi-modal elements such as text, tables, charts, and images. This task is essential for extracting and utilizing the vast amounts of information contained in documents generated annually. One of the critical challenges lies in understanding long-context documents that…
Evaluating conversational AI assistants, like GitHub Copilot Chat, is challenging due to their reliance on language models and chat-based interfaces. Existing metrics for conversational quality need to be revised for domain-specific dialogues, making it hard for software developers to assess the effectiveness of these tools. While techniques like SPUR use large language models to analyze…
Many developers face the challenge of safely executing AI-generated code. Running such code locally can pose security risks and may require extensive setup. Additionally, there’s a need for a tool that can support multiple programming languages and frameworks seamlessly without compromising on security or functionality. Existing solutions offer partial answers to this problem. Some platforms…
Large language models (LLMs) have significantly advanced various natural language processing tasks, but they still face substantial challenges in complex mathematical reasoning. The primary problem researchers are trying to solve is how to enable open-source LLMs to effectively handle complex mathematical tasks. Current methodologies struggle with task decomposition for complex problems and fail to provide…
Due to the complexity of interpreting user questions, database schemas, and SQL production, accurately generating SQL from natural language queries (text-to-SQL) has been a long-standing difficulty. Traditional text-to-SQL systems using deep neural networks and human engineering have succeeded. Then, text-to-SQL jobs were tackled with pre-trained language models (PLMs), and they showed great promise. Problems arise…
The growth of low-quality data on the internet leads to the instillation of undesirable, unsafe, or toxic knowledge in large language models (LLMs). When these models are used in chatbots, they increase the risk of exposing users to harmful advice or aggressive behavior. Existing toxicity evaluation datasets, primarily focused on English, fail to capture multilingual…
Survey on Machine Learning-Powered Augmented Reality in Education: ML advances augmented reality (AR) across various educational fields, enhancing object visualizations and interaction capabilities. This survey outlines the integration of ML in AR, discussing its applications from kindergarten to university. It explores ML models like support vector machines, CNNs, and ANNs in AR education. The survey…
This Paper addresses the limitations of classical machine learning approaches primarily developed for data lying in Euclidean space. Modern machine learning increasingly encounters richly structured data that is inherently non-Euclidean, exhibiting intricate geometric, topological, and algebraic structures. Extracting knowledge from such non-Euclidean data necessitates a broader mathematical perspective beyond the traditional Euclidean framework. Traditional machine…
Large language models (LLMs), like ChatGPT, are reshaping education by offering new methods for learning and teaching. These advanced models understand and generate human-like text, changing student, educator, and information interaction. LLMs enhance learning efficiency and creativity but raise concerns about trust and potential dependency on technology. The core issue explored in this research is…
Deepset and Mixedbread have taken a bold step toward addressing the imbalance in the AI landscape that predominantly favors English-speaking markets. They have introduced a groundbreaking open-source German/English embedding model, deepset-mxbai-embed-de-large-v1, to enhance multilingual capabilities in natural language processing (NLP). This model is based on intfloat/multilingual-e5-large and has undergone fine-tuning on over 30 million pairs…