Token Limit

Large Language Model

A neural network trained on massive text corpora that can generate, understand, and reason about natural language.

GPT

Generative Pre-trained Transformer — a family of autoregressive language models that generate text by predicting the next token.

BERT

Bidirectional Encoder Representations from Transformers — a language model that understands context by reading text in both directions.

Tokenisation

The process of breaking text into smaller units (tokens) such as words, subwords, or characters for processing by language models.

Language Model

A probabilistic model that assigns probabilities to sequences of words, enabling prediction of the next word in a sequence.

Contextual Embedding

Word representations that change based on surrounding context, capturing polysemy and contextual meaning.

Word2Vec

A neural network model that learns distributed word representations by predicting surrounding context words.

GloVe

Global Vectors for Word Representation — an unsupervised learning algorithm for obtaining word vector representations from aggregated word co-occurrence statistics.

Instruction Tuning

Training a language model to follow natural language instructions by fine-tuning on instruction-response pairs.

RLHF

Reinforcement Learning from Human Feedback — a technique for aligning language models with human preferences through reward modelling.

Grounding

Connecting language model outputs to real-world knowledge, facts, or data sources to improve factual accuracy.

Hallucination Detection

Techniques for identifying when AI language models generate plausible but factually incorrect or unsupported content.

A database optimised for storing and querying high-dimensional vector embeddings for similarity search.

The computational study of people's opinions, emotions, and attitudes expressed in text.

A language model trained on text from dozens or hundreds of languages simultaneously, enabling cross-lingual understanding and generation without language-specific fine-tuning.

A subword tokenisation algorithm that iteratively merges the most frequent character pairs to build a vocabulary.

The task of extracting specific parameter values from user utterances to fulfil a detected intent, such as identifying dates, locations, and names in booking requests.

The use of AI to automatically translate text or speech from one natural language to another.

A neural network architecture that maps an input sequence to an output sequence, used in translation and summarisation.

The generation of machine-readable formatted responses such as JSON, XML, or code from language models, enabling reliable integration with downstream software systems.