Large Language Model
Executive Summary
Key Takeaways
- ✓ A large language model is a machine learning model trained on very large volumes of text to predict and generate coherent, contextually relevant language, forming the basis of most generative AI tools used in finance today.
- ✓ An LLM's fluency, how natural and confident its output reads, is not itself evidence that the output is factually accurate, a distinction that is central to using LLMs reliably.
- ✓ LLMs are the underlying technology behind generative AI applications in finance, drafting, narrative commentary, and conversational assistants, addressed throughout this domain.
- ✓ Because an LLM generates language by predicting plausible continuations rather than by retrieving verified facts, any specific factual claim it produces should be independently verified before use in material supporting a decision.
Definition¶
A large language model (LLM) is a machine learning model trained on very large volumes of text to predict and generate coherent, contextually relevant language.
Fluency Is Not Accuracy¶
An LLM generates language by predicting a plausible continuation of a given prompt, based on patterns learned across its training data, not by retrieving or verifying discrete facts from a trusted source. This means fluent, confident-sounding output carries no inherent guarantee of factual accuracy, the foundational reason any specific factual claim an LLM produces should be independently verified before it is relied upon.
Why It Matters to Finance¶
LLMs form the underlying technology behind most generative AI applications used in finance today, drafting assistants, summarisation tools, and conversational AI copilots, addressed in full in Generative AI in Financial Modelling.
Continue Reading¶
Related Pillars¶
Related Technical Guides¶
Related Glossary¶
How OXXON tests thisRun a free structural check with FMAE
Frequently Asked Questions
What is a large language model?
A machine learning model trained on very large volumes of text to predict and generate coherent, contextually relevant language, forming the underlying technology behind most generative AI tools used in finance today.
Does an LLM's fluent output mean it is factually accurate?
No. An LLM generates language by predicting plausible continuations based on patterns learned from its training data, not by retrieving or verifying facts, so fluent, confident-sounding output carries no inherent guarantee of factual accuracy.
What finance applications are built on large language models?
Most generative AI applications used in finance today, drafting assistants, summarisation tools, and conversational copilots, are built on large language models, addressed in Generative AI in Financial Modelling and AI Copilot.
How should factual claims produced by an LLM be treated?
As unverified until independently checked against a reliable source, since the model's method of generating language, predicting plausible continuations, does not guarantee the factual accuracy of any specific claim it produces.
Related Articles
AI Financial Modelling & Artificial Intelligence in Finance
AI financial modelling is the application of machine learning and generative AI techniques within the financial modelling process itself, driver identification, construction assistance, scenario generation, and narrative drafting, while artificial intelligence in finance is the broader application of those same technique categories across the finance function generally. This page is the hub for the Knowledge Centre's AI financial modelling content: the foundational distinction between machine learning, natural language processing, and generative AI; how AI accelerates modelling construction without replacing the auditable calculation layer beneath it; a staged framework for adopting AI reliably; enterprise applications across FP&A, forecasting, valuation, and investment analysis; governance and risk practice; and the institutional best practice synthesis this domain builds toward.
Generative AI
Generative AI is a category of artificial intelligence technique, most commonly a large language model, that produces new language or content, text, summaries, drafted formulas, in response to a prompt. In finance, it is well suited to drafting, summarisation, and narrative tasks, and is distinct from machine learning, which predicts or classifies from structured historical data rather than generating new content.
AI Copilot
An AI copilot is a generative AI assistant, typically built on a large language model, embedded directly within a finance workflow tool, a spreadsheet, an FP&A platform, a reporting system, to support tasks such as drafting, formula assistance, and summarisation through an interactive, conversational interface. A copilot accelerates specific tasks within existing workflow; it does not itself constitute a verification or governance control over the output it produces.
Generative AI in Financial Modelling
Generative AI, large language models applied to drafting and language tasks, has a specific and bounded role in financial modelling: accelerating structure, formatting, and narrative drafting, not producing verified numerical output. This guide sets out that role in detail, the specific failure modes generative AI introduces into a modelling workflow, hallucinated figures, plausible-but-incorrect formula logic, and unverifiable citations, and the concrete review practices that contain each failure mode.