Natural language generation

A computer-implemented method comprising:

• receiving first input data corresponding to a natural language input;
• determining first personality data associated with the natural language input, the first personality data representing a first personality determined to be associated with a response to the natural language input;
• determining first prompt data including the first input data and the first personality data, the first prompt data corresponding to a first natural language directive for a language model to generate a first response to the natural language input, wherein the first response is to be associated with the first personality data;
• processing, using the language model, the first prompt data to generate first model output data, the first model output data indicating that a first component is to generate first data associated with the first input data;
• receiving, from the first component, first natural language data associated with the first input data;
• processing, using the language model, the first prompt data and the first natural language data to generate second model output data responsive to the natural language input, wherein the second model output data corresponds to the first personality data;
• processing the second model output data to generate the first output data responsive to the natural language input;
• and
• causing presentation of the first output data.

A computing system comprising:

• at least one processor;
• and
• at least one memory comprising instructions that, when executed by the at least one processor, cause the computing system to:
• receive first input data corresponding to a natural language input;
• determine first personality data associated with the natural language input, the first personality data representing a first personality determined to be associated with a response to the natural language input;
• determine first prompt data including the first input data and the first personality data, the first prompt data corresponding to a first natural language directive for a language model to generate a first response to the natural language input, wherein the first response is to be associated with the first personality data;
• process, using the language model, the first prompt data to generate first model output data, the first model output data indicating that a first component is to generate first data associated with the first input data;
• receive, from the first component, first natural language data associated with the first input data;
• process, using the language model, the first prompt data and the first natural language data to generate second model output data responsive to the natural language input, wherein the second model output data corresponds to the first personality data;
• process the second model output data to generate the first output data responsive to the natural language input;
• and
• cause presentation of the first output data.