Language Model

The field of large language models (LLMs), a subset of artificial intelligence that attempts to mimic human-like understanding and decision-making, is a focus for considerable research efforts. These systems need to be versatile and broadly intelligent, which means a complex development process that can avoid "hallucination", or the production of nonsensical outputs. Traditional training methods…

KAIST AI's introduction of the Odds Ratio Preference Optimization (ORPO) represents a novel approach in the field of pre-trained language models (PLMs), one that may revolutionize model alignment and set a new standard for ethical artificial intelligence (AI). In contrast to traditional methods, which heavily rely on supervised fine-tuning (SFT) and reinforcement learning with human…

The emergence of large language models (LLMs) is making significant advancements in machine learning, offering the ability to mimic human language which is critical for many modern technologies from content creation to digital assistants. A major obstacle to progress, however, has been the processing speed when generating textual responses. This is largely due to the…

The rapid increase in available scientific literature presents a challenging environment for researchers. Current Language Learning Models (LLMs) are proficient at extracting text-based information but struggle with important multimodal data, including charts and molecular structures, found in scientific texts. In response to this problem, researchers from DP Technology and AI for Science Institute, Beijing, have…

Large language models (LLMs) have emerged as powerful tools in artificial intelligence, providing improvements in areas such as conversational AI and complex analytical tasks. However, while these models have the capacity to sift through and apply extensive amounts of data, they also face significant challenges, particularly in the field of 'knowledge conflicts'. Knowledge conflicts occur when…

Large language models (LLMs) have made significant strides in the field of artificial intelligence, paving the way for machines that understand and generate human-like text. However, these models face the inherent challenge of their knowledge being fixed at the point of their training, limiting their adaptability and ability to incorporate new information post-training. This proves…

Artificial intelligence (AI) researchers from Stanford University and Notbad AI Inc are striving to improve language models' AI capabilities in interpreting and generating nuanced, human-like text. Their project, called Quiet Self-Taught Reasoner (Quiet-STaR), embeds reasoning capabilities directly into language models. Unlike previous methods, which focused on training models using specific datasets for particular tasks, Quiet-STaR…

Computer vision, the field dealing with how computers can gain understanding from digital images or videos, has seen remarkable growth in recent years. A significant challenge within this field is the precise interpretation of intricate image details, understanding both global and local visual cues. Despite advances with conventional models like Convolutional Neural Networks (CNNs) and…