Previous research on reasoning frameworks in large language models (LLMs) has explored various approaches to enhance problem-solving capabilities. Chain-of-Thought (CoT) introduced articulated reasoning processes, while Tree-of-Thought (ToT) and Graph-of-Thought (GoT) expanded on this concept by incorporating branching possibilities and complex relationships between reasoning steps. Cumulative Reasoning (CR) introduced collaborative processes involving multiple specialized LLMs. These…
While LLMs have shown promise in natural language processing, they often need help to perform multi-step reasoning and problem-solving, particularly in areas that require abstract thinking and drawing inferences from incomplete or fragmented information. The ability to reason effectively is crucial for LLMs to be truly useful in real-world applications. This limitation hinders the application…
Neural networks are widely adopted in various fields due to their ability to model complex patterns and relationships. However, they face a critical vulnerability to adversarial attacks – small, malicious input changes that cause unpredictable outputs. This issue poses significant challenges to the reliability and security of machine learning models across various applications. While several…
In recent research, a state-of-the-art technique has been introduced for utilizing Large Language Models (LLMs) to verify RDF (Resource Description Framework) triples, emphasizing the significance of providing traceable and verifiable reasoning. The fundamental building blocks of knowledge graphs (KGs) are RDF triples, which are composed of subject-predicate-object statements that describe relationships or facts. Maintaining the…
LLMs exhibit remarkable language abilities, prompting questions about their memory mechanisms. Unlike humans, who use memory for daily tasks, LLMs’ “memory” is derived from input rather than stored externally. Research efforts have aimed to improve LLMs’ retention by extending context length and incorporating external memory systems. However, these methods do not fully clarify how memory…
Novak Zivanic has made a significant contribution to the field of Natural Language Processing with the release of Embedić, a suite of Serbian text embedding models. These models are specifically designed for Information Retrieval and Retrieval-Augmented Generation (RAG) tasks. Specifically, the smallest model in the suite has achieved a remarkable feat, surpassing the previous state-of-the-art…
The release of Pixtral 12B by Mistral AI represents a groundbreaking leap in the multimodal large language model powered by an impressive 12 billion parameters. This advanced AI model is designed to handle and generate textual and visual content, making it a versatile tool for various industries. Capable of processing massive datasets and delivering highly…
Text embedding models have become foundational in natural language processing (NLP). These models convert text into high-dimensional vectors that capture semantic relationships, enabling tasks like document retrieval, classification, clustering, and more. Embeddings are especially critical in advanced systems such as Retrieval-Augmented Generation (RAG) models, where the embeddings support retrieving relevant documents. With the increasing need…
Software engineering integrates principles from computer science to design, develop, and maintain software applications. As technology advances, the complexity of software systems increases, creating challenges in ensuring efficiency, accuracy, and overall performance. Artificial intelligence, particularly using Large Language Models (LLMs), has significantly impacted this field. LLMs now automate tasks like code generation, debugging, and software…
The significant advancements in Large Language Models (LLMs) have led to the development of agentic systems, which integrate several tools and APIs to fulfill user inquiries through function calls. By interpreting natural language commands, these systems can perform sophisticated tasks independently, such as information retrieval and device control. However, much research hasn’t been done on…