Models & architecture
Large language model
A foundation model trained to understand and generate sequences of language tokens.
Also known as: LLM
Definition
A large language model predicts and generates token sequences using patterns learned from extensive text and code datasets.
Why it matters
An LLM is only one component of an enterprise application; prompts, retrieval, tools and controls determine actual banking outcomes.
Related concepts
- Foundation model
A large pre-trained model adaptable to many downstream tasks.
- System under test
The complete configuration being evaluated—not only the model.
- Token
A unit of text processed or generated by a language model.