Large Language Model (LLM)

A deep-learning model trained on massive text corpora to generate and understand natural language.

At a minimum, a language model having a very high number of parameters. More informally, any Transformer-based language model, such as Gemini or GPT.

See Large language models (LLMs) in Machine Learning Crash Course for more information.

1.
Claude 3.5 Sonnet by Anthropic is used by Slack for its AI summarisation and search features, processing billions of messages to generate concise channel summaries and answer questions about team history.
2.
Mistral 7B is deployed on-premises by a European government ministry for citizen-service automation - the LLM processes natural-language queries and generates responses grounded in official government documents.
3.
LLaMA 3.1 8B is fine-tuned by a legal-tech startup on 50,000 annotated contracts to create a specialised contract-review LLM that outperforms GPT-4o on legal-clause extraction at 10% of the API cost.

Created for this library

1.
An enterprise legal team uses a large language model with retrieval grounding to draft first-pass contract reviews on internal clause libraries.
2.
A healthcare provider uses a large language model with grounded retrieval on policy documents to answer staff questions accurately.
3.
A financial services firm uses a large language model with strict retrieval grounding on filings to assist analysts during earnings season.

A deep-learning model trained on massive text corpora to generate and understand natural language.

At a minimum, a language model having a very high number of parameters. More informally, any Transformer-based language model, such as Gemini or GPT.

See Large language models (LLMs) in Machine Learning Crash Course for more information.

1.
Claude 3.5 Sonnet by Anthropic is used by Slack for its AI summarisation and search features, processing billions of messages to generate concise channel summaries and answer questions about team history.
2.
Mistral 7B is deployed on-premises by a European government ministry for citizen-service automation - the LLM processes natural-language queries and generates responses grounded in official government documents.
3.
LLaMA 3.1 8B is fine-tuned by a legal-tech startup on 50,000 annotated contracts to create a specialised contract-review LLM that outperforms GPT-4o on legal-clause extraction at 10% of the API cost.

Created for this library

1.
An enterprise legal team uses a large language model with retrieval grounding to draft first-pass contract reviews on internal clause libraries.
2.
A healthcare provider uses a large language model with grounded retrieval on policy documents to answer staff questions accurately.
3.
A financial services firm uses a large language model with strict retrieval grounding on filings to assist analysts during earnings season.

Large Language ModelLLM