Chain-of-Thought Prompting

Prompt Engineering

The practice of designing and optimising input prompts to elicit desired outputs from large language models.

Few-Shot Prompting

A technique where a language model is given a small number of examples within the prompt to guide its response pattern.

Zero-Shot Prompting

Querying a language model to perform a task it was not explicitly trained on, without providing any examples in the prompt.

In-Context Learning

The ability of large language models to learn new tasks from examples provided within the input prompt without parameter updates.

Few-Shot Learning

A machine learning approach where models learn to perform tasks from only a small number of labelled examples, often achieved through in-context learning in large language models.

Zero-Shot Learning

The ability of AI models to perform tasks they were not explicitly trained on, using generalised knowledge and instruction-following capabilities.

Emergent Capabilities

Abilities that appear in large language models at certain scale thresholds that were not present in smaller versions, such as in-context learning and complex reasoning.

Tool Use in AI

The capability of AI agents to invoke external tools, APIs, databases, and software applications to accomplish tasks beyond the model's intrinsic knowledge and abilities.

System Prompt

An initial instruction set provided to a language model that defines its persona, constraints, output format, and behavioural guidelines for a given session or application.

A form of logical inference that seeks the simplest and most likely explanation for a set of observations.

The process of teaching an AI model to recognise patterns by exposing it to large datasets and adjusting its parameters.

The creation of artificially produced datasets that mimic the statistical properties of real-world data, used for training AI models while preserving privacy.

A graphical plot illustrating the diagnostic ability of a binary classifier as its discrimination threshold is varied.

Google's custom-designed application-specific integrated circuit for accelerating machine learning workloads.

A degradation phenomenon where AI models trained on AI-generated data progressively lose diversity and accuracy, converging toward a narrow distribution of outputs.

A technique combining information retrieval with text generation, allowing AI to access external knowledge before generating responses.

A machine learning approach where models are trained across decentralised devices without sharing raw data, preserving privacy.