Skip to main content

An Overview of Terms

This guide provides a foundational understanding of key terms in the field of AI and LLMs, suitable for beginners or non-tech professionals. The field is rapidly evolving, so staying updated with the latest developments is important.

  1. Fine Tuning: This refers to the process of adjusting a pre-trained model (like an LLM) on a specific dataset or for a specific task. The idea is to refine the model's abilities to better respond to the nuances of a particular domain or requirement. For example, an LLM trained on general data might be fine-tuned on legal documents to improve its performance in legal contexts.

  2. Hallucinations: In the context of LLMs, hallucinations refer to instances where the model generates incorrect or nonsensical information, often with confidence. These are not deliberate fabrications but result from the model's limitations in understanding context or factual accuracy.

  3. GPT (Generative Pre-trained Transformer): A type of LLM known for its ability to generate human-like text. It's pre-trained on a vast corpus of text and then fine-tuned for specific tasks.

  4. Transformer Models: A type of neural network architecture that's particularly effective for processing sequences of data, like text. Transformers are the backbone of many modern LLMs, including GPT models.

  5. Natural Language Processing (NLP): The field in AI focused on enabling machines to understand, interpret, and respond to human language.

  6. Machine Learning (ML): A branch of AI that focuses on building algorithms that can learn from and make predictions or decisions based on data.

  7. Artificial Neural Networks (ANN): Computational models inspired by the human brain, used in ML to process complex patterns in large amounts of data.

  8. Deep Learning: A subset of ML that uses multi-layered neural networks to analyze various factors of data, often used for more complex tasks like image and speech recognition.

  9. Chatbot: A software application used to conduct an online chat conversation via text or text-to-speech, in lieu of providing direct contact with a human agent. Often powered by LLMs.

  10. Bias in AI: Refers to the tendency of AI models to produce results that are systemically prejudiced due to erroneous assumptions in the machine learning process.

  11. Prompt Engineering: The process of designing and refining input prompts to effectively guide an AI model's responses towards desired outcomes or specific types of information.