Several significant benchmarks have been developed to evaluate language understanding and specific applications of large language models (LLMs). Notable benchmarks include GLUE, SuperGLUE, ANLI, LAMA, TruthfulQA, and Persuasion for Good, which assess LLMs on tasks such as sentiment analysis, commonsense reasoning, and factual accuracy. However, limited work has specifically targeted fraud and abuse detection using… →

Anthropic, a company known for its commitment to creating AI systems that prioritize safety, transparency, and alignment with human values, has introduced Claude for Enterprise to meet the growing demands of businesses seeking reliable, ethical AI solutions. As organizations increasingly adopt AI technologies to enhance productivity and streamline operations, Claude for Enterprise emerges as a… →

The landscape of large language models (LLMs) for coding has been enriched with the release of Yi-Coder by 01.AI, a series of open-source models designed for efficient and powerful coding performance. Despite its relatively small size, Yi-Coder delivers state-of-the-art results, positioning itself as a formidable code generation and completion player. Available in two configurations, 1.5… →

Gregor Betz from Logikon AI, KIT introduces Guided Reasoning. A system with more than one agent is a Guided Reasoning system if one agent, called the guide, mostly works with the other agents to improve their Reasoning. A multi-agent system with a guide agent and at least one client agent is called a Guided Reasoning… →

Large pre-trained generative transformers have demonstrated exceptional performance in various natural language generation tasks, using large training datasets to capture the logic of human language. However, adapting these models for certain applications through fine-tuning poses significant challenges. The computational efficiency of fine-tuning depends heavily on the model size, making it costly for researchers to work… →

Large Language Models (LLMs) have demonstrated great performance in Natural Language Processing (NLP) applications. However, they have high computational costs when fine-tuning them, which can lead to incorrect information being generated, i.e., hallucinations. Two viable strategies have been established to solve these problems: parameter-efficient methods such as Low-Rank Adaptation (LoRA) to minimize computing demands and… →

Machine learning has revolutionized various fields, offering powerful tools for data analysis and predictive modeling. Central to these models’ success is hyperparameter optimization (HPO), where the parameters that govern the learning process are tuned to achieve the best possible performance. HPO involves selecting hyperparameter values such as learning rates, regularization coefficients, and network architectures. These… →